test the version without pandas

In [1]:

    

import sys
dossier = '/home/benjamin/Documents/eviacybernetics/Projets/Grevia'
sys.path.append(dossier)
import grevia


    

In [2]:

    

import importlib
importlib.reload(grevia.graph_structure)
importlib.reload(grevia)


    

    
Out[2]:





<module 'grevia' from '/home/benjamin/Documents/eviacybernetics/Projets/Grevia/grevia/__init__.py'>

In [4]:

    

import networkx as nx
G = nx.read_gpickle('/media/benjamin/Largo/testspdfs/pickle/graph.pkl')


    

In [6]:

    

G.size()


    

    
Out[6]:





5353

In [8]:

    

edge_info = G.edges(data=True)


    

In [17]:

    

edge_sorted = sorted(edge_info, key=lambda edge: edge[2]['weight'], reverse=True)


    

In [19]:

    

edge_sorted[:None]


    

    
Out[19]:





[('08_15',
  '08_15',
  {'paths': {'29': {'word_positions': [130,
      132,
      134,
      136,
      138,
      140,
      142,
      144,
      146,
      148,
      150,
      152,
      154,
      156,
      158,
      160,
      162,
      164,
      166,
      168,
      170,
      172]}},
   'weight': 22}),
 ('contrat',
  'de_travail',
  {'paths': {'0': {'word_positions': [46]},
    '1': {'word_positions': [103, 61]},
    '14': {'word_positions': [98, 120, 580, 296, 247, 40, 425, 473]},
    '16': {'word_positions': [64, 129, 107]},
    '19': {'word_positions': [52]},
    '31': {'word_positions': [65, 107]},
    '4': {'word_positions': [64, 129, 107]}},
   'weight': 20}),
 ('numero_de',
  'prestation_inchange',
  {'paths': {'11': {'word_positions': [223,
      128,
      162,
      196,
      256,
      232,
      138,
      171,
      205,
      239,
      145,
      180,
      214,
      247,
      155,
      188]},
    '15': {'word_positions': [139, 132]}},
   'weight': 18}),
 ('253_rue',
  'du_miroir',
  {'paths': {'1': {'word_positions': [68]},
    '11': {'word_positions': [26]},
    '14': {'word_positions': [65, 438]},
    '15': {'word_positions': [28]},
    '16': {'word_positions': [72]},
    '2': {'word_positions': [46]},
    '25': {'word_positions': [46]},
    '29': {'word_positions': [25]},
    '34': {'word_positions': [25]},
    '36': {'word_positions': [34, 167]},
    '37': {'word_positions': [46]},
    '4': {'word_positions': [72]},
    '5': {'word_positions': [46]},
    '6': {'word_positions': [79]},
    '7': {'word_positions': [46]},
    '9': {'word_positions': [314]}},
   'weight': 18}),
 ('de_votre',
  'contrat',
  {'paths': {'1': {'word_positions': [60, 102]},
    '14': {'word_positions': [97, 295, 39, 119, 424, 472, 246]},
    '16': {'word_positions': [106, 128, 63]},
    '31': {'word_positions': [106, 64]},
    '4': {'word_positions': [106, 128, 63]}},
   'weight': 17}),
 ('rh',
  'epfl_ch',
  {'paths': {'0': {'word_positions': [27]},
    '1': {'word_positions': [25]},
    '14': {'word_positions': [219]},
    '16': {'word_positions': [47, 29]},
    '2': {'word_positions': [26]},
    '25': {'word_positions': [26]},
    '29': {'word_positions': [15]},
    '31': {'word_positions': [25]},
    '36': {'word_positions': [191, 10]},
    '37': {'word_positions': [26]},
    '4': {'word_positions': [47, 29]},
    '5': {'word_positions': [26]},
    '7': {'word_positions': [26]}},
   'weight': 16}),
 ('370_00',
  '370_00',
  {'paths': {'36': {'word_positions': [512,
      514,
      516,
      518,
      520,
      529,
      531,
      533,
      535,
      537,
      539,
      510]}},
   'weight': 12}),
 ('1015_lausanne',
  'site_web',
  {'paths': {'0': {'word_positions': [35]},
    '1': {'word_positions': [39]},
    '14': {'word_positions': [224, 403, 19, 572]},
    '16': {'word_positions': [42]},
    '19': {'word_positions': [41]},
    '31': {'word_positions': [43]},
    '4': {'word_positions': [42]}},
   'weight': 10}),
 ('756_4236',
  '5600_57',
  {'paths': {'2': {'word_positions': [52]},
    '22': {'word_positions': [39, 227]},
    '25': {'word_positions': [52]},
    '26': {'word_positions': [39]},
    '36': {'word_positions': [40, 204]},
    '37': {'word_positions': [52]},
    '5': {'word_positions': [52]},
    '7': {'word_positions': [52]}},
   'weight': 10}),
 ('ecole_polytechnique',
  'fédérale',
  {'paths': {'0': {'word_positions': [56]},
    '14': {'word_positions': [590]},
    '19': {'word_positions': [64]},
    '2': {'word_positions': [30]},
    '22': {'word_positions': [22]},
    '25': {'word_positions': [30]},
    '26': {'word_positions': [22]},
    '37': {'word_positions': [30]},
    '5': {'word_positions': [30]},
    '7': {'word_positions': [30]}},
   'weight': 10}),
 ('230_00',
  'allocation_familiale',
  {'paths': {'2': {'word_positions': [106, 127]},
    '25': {'word_positions': [121, 100]},
    '37': {'word_positions': [121, 100]},
    '5': {'word_positions': [121, 100]},
    '7': {'word_positions': [106, 127]}},
   'weight': 10}),
 ('de',
  'bien_vouloir',
  {'paths': {'1': {'word_positions': [117]},
    '11': {'word_positions': [70]},
    '14': {'word_positions': [135, 487, 310]},
    '15': {'word_positions': [72]},
    '16': {'word_positions': [144]},
    '31': {'word_positions': [121]},
    '4': {'word_positions': [144]}},
   'weight': 9}),
 ('12_15',
  '8_195',
  {'paths': {'7': {'word_positions': [193,
      293,
      244,
      181,
      280,
      169,
      268,
      306,
      158]}},
   'weight': 9}),
 ('monsieur_le',
  'professeur_pierre',
  {'paths': {'1': {'word_positions': [171]},
    '14': {'word_positions': [178, 532, 357, 798]},
    '16': {'word_positions': [196]},
    '19': {'word_positions': [277]},
    '31': {'word_positions': [177]},
    '4': {'word_positions': [196]}},
   'weight': 9}),
 ('08_16',
  '7_680',
  {'paths': {'5': {'word_positions': [175,
      287,
      274,
      163,
      262,
      152,
      187,
      300,
      238]}},
   'weight': 9}),
 ('fédérale',
  'de_lausanne',
  {'paths': {'0': {'word_positions': [57]},
    '14': {'word_positions': [591]},
    '19': {'word_positions': [65]},
    '2': {'word_positions': [31]},
    '25': {'word_positions': [31]},
    '36': {'word_positions': [19]},
    '37': {'word_positions': [31]},
    '5': {'word_positions': [31]},
    '7': {'word_positions': [31]}},
   'weight': 9}),
 ('4121_693',
  '35_95',
  {'paths': {'0': {'word_positions': [20]},
    '1': {'word_positions': [18]},
    '14': {'word_positions': [391, 558, 212, 46]},
    '16': {'word_positions': [22]},
    '31': {'word_positions': [18]},
    '4': {'word_positions': [22]}},
   'weight': 9}),
 ('12_14',
  '7_945',
  {'paths': {'2': {'word_positions': [159,
      258,
      148,
      296,
      183,
      283,
      234,
      171,
      270]}},
   'weight': 9}),
 ('00',
  '02_00',
  {'paths': {'1': {'word_positions': [47]},
    '14': {'word_positions': [233, 26, 411]},
    '16': {'word_positions': [50]},
    '19': {'word_positions': [71]},
    '31': {'word_positions': [51]},
    '4': {'word_positions': [50]}},
   'weight': 8}),
 ('mme',
  'numero_de',
  {'paths': {'11': {'word_positions': [194,
      169,
      203,
      254,
      178,
      212,
      153,
      221]}},
   'weight': 8}),
 ('no_avs',
  '756_4236',
  {'paths': {'2': {'word_positions': [50]},
    '25': {'word_positions': [50]},
    '29': {'word_positions': [46]},
    '36': {'word_positions': [202, 38]},
    '37': {'word_positions': [50]},
    '5': {'word_positions': [50]},
    '7': {'word_positions': [50]}},
   'weight': 8}),
 ('emp_04',
  '15',
  {'paths': {'36': {'word_positions': [83, 70, 423, 408, 122, 416, 109, 96]}},
   'weight': 8}),
 ('et',
  'survivant_s',
  {'paths': {'2': {'word_positions': [6]},
    '25': {'word_positions': [6]},
    '29': {'word_positions': [317]},
    '36': {'word_positions': [551, 146]},
    '37': {'word_positions': [6]},
    '5': {'word_positions': [6]},
    '7': {'word_positions': [6]}},
   'weight': 8}),
 ('ch',
  '1015_lausanne',
  {'paths': {'0': {'word_positions': [33]},
    '14': {'word_positions': [17, 570, 401, 222]},
    '31': {'word_positions': [41]},
    '36': {'word_positions': [7, 188]}},
   'weight': 8}),
 ('35_95',
  'station_7',
  {'paths': {'0': {'word_positions': [22]},
    '1': {'word_positions': [20]},
    '14': {'word_positions': [393, 560, 214]},
    '16': {'word_positions': [24]},
    '31': {'word_positions': [20]},
    '4': {'word_positions': [24]}},
   'weight': 8}),
 ('station_7',
  'e_mail',
  {'paths': {'0': {'word_positions': [24]},
    '1': {'word_positions': [22]},
    '14': {'word_positions': [216, 395, 14]},
    '16': {'word_positions': [26]},
    '31': {'word_positions': [22]},
    '4': {'word_positions': [26]}},
   'weight': 8}),
 ('7_680',
  '80',
  {'paths': {'37': {'word_positions': [276, 165, 264, 89]},
    '5': {'word_positions': [276, 165, 264, 89]}},
   'weight': 8}),
 ('7_680',
  '80_0',
  {'paths': {'37': {'word_positions': [177, 289, 189, 302]},
    '5': {'word_positions': [177, 289, 189, 302]}},
   'weight': 8}),
 ('allocation_familiale',
  'epp',
  {'paths': {'2': {'word_positions': [129, 108]},
    '36': {'word_positions': [292, 279]},
    '5': {'word_positions': [123, 102]},
    '7': {'word_positions': [129, 108]}},
   'weight': 8}),
 ('ce_vieillesse',
  'et',
  {'paths': {'2': {'word_positions': [5]},
    '25': {'word_positions': [5]},
    '29': {'word_positions': [316]},
    '36': {'word_positions': [145, 550]},
    '37': {'word_positions': [5]},
    '5': {'word_positions': [5]},
    '7': {'word_positions': [5]}},
   'weight': 8}),
 ('personnel_monsieur',
  'benjamin_ricaud',
  {'paths': {'2': {'word_positions': [40]},
    '25': {'word_positions': [40]},
    '29': {'word_positions': [21]},
    '36': {'word_positions': [163, 28]},
    '37': {'word_positions': [40]},
    '5': {'word_positions': [40]},
    '7': {'word_positions': [40]}},
   'weight': 8}),
 ('professeur_pierre',
  'vandergheynst',
  {'paths': {'1': {'word_positions': [173]},
    '14': {'word_positions': [180, 534, 359]},
    '16': {'word_positions': [198]},
    '31': {'word_positions': [179]},
    '4': {'word_positions': [198]}},
   'weight': 7}),
 ('copie_à',
  'monsieur_le',
  {'paths': {'1': {'word_positions': [169]},
    '14': {'word_positions': [530, 355, 176]},
    '16': {'word_positions': [194]},
    '31': {'word_positions': [175]},
    '4': {'word_positions': [194]}},
   'weight': 7}),
 ('et_signée',
  'par',
  {'paths': {'1': {'word_positions': [135]},
    '14': {'word_positions': [153, 505, 328]},
    '16': {'word_positions': [162]},
    '31': {'word_positions': [139]},
    '4': {'word_positions': [162]}},
   'weight': 7}),
 ('1015_lausanne',
  'rh',
  {'paths': {'2': {'word_positions': [25]},
    '25': {'word_positions': [25]},
    '36': {'word_positions': [9, 190]},
    '37': {'word_positions': [25]},
    '5': {'word_positions': [25]},
    '7': {'word_positions': [25]}},
   'weight': 7}),
 ('suvapassuran',
  'ce_accident',
  {'paths': {'2': {'word_positions': [17]},
    '25': {'word_positions': [17]},
    '36': {'word_positions': [562, 156]},
    '37': {'word_positions': [17]},
    '5': {'word_positions': [17]},
    '7': {'word_positions': [17]}},
   'weight': 7}),
 ('nous_vous',
  'présentons',
  {'paths': {'1': {'word_positions': [144]},
    '14': {'word_positions': [337, 162, 514]},
    '16': {'word_positions': [171]},
    '31': {'word_positions': [148]},
    '4': {'word_positions': [171]}},
   'weight': 7}),
 ('nous_vous',
  'saurions_gré',
  {'paths': {'1': {'word_positions': [114]},
    '14': {'word_positions': [307, 132, 484]},
    '16': {'word_positions': [141]},
    '31': {'word_positions': [118]},
    '4': {'word_positions': [141]}},
   'weight': 7}),
 ('l_employé',
  'e',
  {'paths': {'1': {'word_positions': [160]},
    '14': {'word_positions': [537, 362, 183]},
    '16': {'word_positions': [185]},
    '31': {'word_positions': [165]},
    '4': {'word_positions': [185]}},
   'weight': 7}),
 ('date_d',
  'échéance',
  {'paths': {'1': {'word_positions': [99]},
    '14': {'word_positions': [292, 469, 94]},
    '16': {'word_positions': [103]},
    '31': {'word_positions': [103]},
    '4': {'word_positions': [103]}},
   'weight': 7}),
 ('02_00',
  '03',
  {'paths': {'1': {'word_positions': [49]},
    '14': {'word_positions': [235, 28, 413]},
    '16': {'word_positions': [52]},
    '31': {'word_positions': [53]},
    '4': {'word_positions': [52]}},
   'weight': 7}),
 ('nous',
  'avons_le',
  {'paths': {'1': {'word_positions': [88]},
    '14': {'word_positions': [281, 458, 84]},
    '16': {'word_positions': [92]},
    '31': {'word_positions': [92]},
    '4': {'word_positions': [92]}},
   'weight': 7}),
 ('nous',
  'confirmer_votre',
  {'paths': {'1': {'word_positions': [120]},
    '14': {'word_positions': [313, 138, 490]},
    '16': {'word_positions': [147]},
    '31': {'word_positions': [124]},
    '4': {'word_positions': [147]}},
   'weight': 7}),
 ('bien_vouloir',
  'nous',
  {'paths': {'1': {'word_positions': [119]},
    '14': {'word_positions': [137, 489, 312]},
    '16': {'word_positions': [146]},
    '31': {'word_positions': [123]},
    '4': {'word_positions': [146]}},
   'weight': 7}),
 ('46_96',
  'n_réf',
  {'paths': {'1': {'word_positions': [52]},
    '14': {'word_positions': [31, 416, 238]},
    '16': {'word_positions': [55]},
    '31': {'word_positions': [56]},
    '4': {'word_positions': [55]}},
   'weight': 7}),
 ('monsieur_nos',
  'salutations',
  {'paths': {'1': {'word_positions': [147]},
    '14': {'word_positions': [517, 340, 165]},
    '16': {'word_positions': [174]},
    '31': {'word_positions': [151]},
    '4': {'word_positions': [174]}},
   'weight': 7}),
 ('confirmer_votre',
  'accord_en',
  {'paths': {'1': {'word_positions': [122]},
    '14': {'word_positions': [315, 140, 492]},
    '16': {'word_positions': [149]},
    '31': {'word_positions': [126]},
    '4': {'word_positions': [149]}},
   'weight': 7}),
 ('salutations',
  'les_meilleures',
  {'paths': {'1': {'word_positions': [148]},
    '14': {'word_positions': [518, 341, 166]},
    '16': {'word_positions': [175]},
    '31': {'word_positions': [152]},
    '4': {'word_positions': [175]}},
   'weight': 7}),
 ('cette_attente',
  'nous_vous',
  {'paths': {'1': {'word_positions': [142]},
    '14': {'word_positions': [512, 335, 160]},
    '16': {'word_positions': [169]},
    '31': {'word_positions': [146]},
    '4': {'word_positions': [169]}},
   'weight': 7}),
 ('la_nouvelle',
  'date_d',
  {'paths': {'1': {'word_positions': [97]},
    '14': {'word_positions': [290, 467, 92]},
    '16': {'word_positions': [101]},
    '31': {'word_positions': [101]},
    '4': {'word_positions': [101]}},
   'weight': 7}),
 ('03',
  '46_96',
  {'paths': {'1': {'word_positions': [50]},
    '14': {'word_positions': [236, 29, 414]},
    '16': {'word_positions': [53]},
    '31': {'word_positions': [54]},
    '4': {'word_positions': [53]}},
   'weight': 7}),
 ('federale',
  'de_lausanne',
  {'paths': {'0': {'word_positions': [30]},
    '14': {'word_positions': [431, 567, 58, 254]},
    '29': {'word_positions': [33]},
    '36': {'word_positions': [175]}},
   'weight': 7}),
 ('thonon',
  'les_bains',
  {'paths': {'11': {'word_positions': [36]},
    '15': {'word_positions': [38]},
    '8': {'word_positions': [50, 723, 710, 155, 729]}},
   'weight': 7}),
 ('4_440',
  'allocation_enfant',
  {'paths': {'36': {'word_positions': [241, 259, 247, 265, 235, 253, 271]}},
   'weight': 7}),
 ('de_pension',
  'an_p',
  {'paths': {'2': {'word_positions': [14]},
    '25': {'word_positions': [14]},
    '29': {'word_positions': [325]},
    '36': {'word_positions': [559]},
    '37': {'word_positions': [14]},
    '5': {'word_positions': [14]},
    '7': {'word_positions': [14]}},
   'weight': 7}),
 ('par',
  'retour_de',
  {'paths': {'1': {'word_positions': [136]},
    '14': {'word_positions': [329, 154, 506]},
    '16': {'word_positions': [163]},
    '31': {'word_positions': [140]},
    '4': {'word_positions': [163]}},
   'weight': 7}),
 ('courrier_dans',
  'cette_attente',
  {'paths': {'1': {'word_positions': [140]},
    '14': {'word_positions': [510, 333, 158]},
    '16': {'word_positions': [167]},
    '31': {'word_positions': [144]},
    '4': {'word_positions': [167]}},
   'weight': 7}),
 ('monsieur',
  'benjamin_ricaud',
  {'paths': {'1': {'word_positions': [64]},
    '14': {'word_positions': [257, 434, 61]},
    '16': {'word_positions': [68]},
    '31': {'word_positions': [68]},
    '4': {'word_positions': [68]}},
   'weight': 7}),
 ('a_été',
  'fixée_au',
  {'paths': {'1': {'word_positions': [107]},
    '14': {'word_positions': [300, 477, 102]},
    '16': {'word_positions': [111]},
    '31': {'word_positions': [111]},
    '4': {'word_positions': [111]}},
   'weight': 7}),
 ('présentons',
  'monsieur_nos',
  {'paths': {'1': {'word_positions': [145]},
    '14': {'word_positions': [515, 338, 163]},
    '16': {'word_positions': [172]},
    '31': {'word_positions': [149]},
    '4': {'word_positions': [172]}},
   'weight': 7}),
 ('décompte',
  'de_salaire',
  {'paths': {'2': {'word_positions': [34]},
    '25': {'word_positions': [34]},
    '29': {'word_positions': [6]},
    '36': {'word_positions': [22]},
    '37': {'word_positions': [34]},
    '5': {'word_positions': [34]},
    '7': {'word_positions': [34]}},
   'weight': 7}),
 ('de_la',
  'présente_dûment',
  {'paths': {'1': {'word_positions': [130]},
    '14': {'word_positions': [323, 148, 500]},
    '16': {'word_positions': [157]},
    '31': {'word_positions': [134]},
    '4': {'word_positions': [157]}},
   'weight': 7}),
 ('7_echelon',
  'page_1',
  {'paths': {'2': {'word_positions': [69]},
    '25': {'word_positions': [69]},
    '29': {'word_positions': [59]},
    '36': {'word_positions': [217]},
    '37': {'word_positions': [69]},
    '5': {'word_positions': [69]},
    '7': {'word_positions': [69]}},
   'weight': 7}),
 ('accord_en',
  'nous_retournant',
  {'paths': {'1': {'word_positions': [124]},
    '14': {'word_positions': [494, 317, 142]},
    '16': {'word_positions': [151]},
    '31': {'word_positions': [128]},
    '4': {'word_positions': [151]}},
   'weight': 7}),
 ('epfl_pl',
  'drh_téléphone',
  {'paths': {'1': {'word_positions': [5]},
    '14': {'word_positions': [376, 4, 198]},
    '16': {'word_positions': [5]},
    '31': {'word_positions': [5]},
    '4': {'word_positions': [5]}},
   'weight': 7}),
 ('benjamin_ricaud',
  '253_rue',
  {'paths': {'1': {'word_positions': [66]},
    '14': {'word_positions': [436, 63]},
    '16': {'word_positions': [70]},
    '29': {'word_positions': [23]},
    '36': {'word_positions': [165]},
    '4': {'word_positions': [70]}},
   'weight': 7}),
 ('cppcaisse',
  'de_pension',
  {'paths': {'2': {'word_positions': [12]},
    '25': {'word_positions': [12]},
    '36': {'word_positions': [152, 557]},
    '37': {'word_positions': [12]},
    '5': {'word_positions': [12]},
    '7': {'word_positions': [12]}},
   'weight': 7}),
 ('datée',
  'et_signée',
  {'paths': {'1': {'word_positions': [133]},
    '14': {'word_positions': [151, 503, 326]},
    '16': {'word_positions': [160]},
    '31': {'word_positions': [137]},
    '4': {'word_positions': [160]}},
   'weight': 7}),
 ('nous_retournant',
  'la_copie',
  {'paths': {'1': {'word_positions': [126]},
    '14': {'word_positions': [319, 144, 496]},
    '16': {'word_positions': [153]},
    '31': {'word_positions': [130]},
    '4': {'word_positions': [153]}},
   'weight': 7}),
 ('la_copie',
  'de_la',
  {'paths': {'1': {'word_positions': [128]},
    '14': {'word_positions': [321, 146, 498]},
    '16': {'word_positions': [155]},
    '31': {'word_positions': [132]},
    '4': {'word_positions': [155]}},
   'weight': 7}),
 ('fixée_au',
  '30_septembre',
  {'paths': {'1': {'word_positions': [109]},
    '14': {'word_positions': [479, 104, 302]},
    '16': {'word_positions': [113]},
    '31': {'word_positions': [113]},
    '4': {'word_positions': [113]}},
   'weight': 7}),
 ('survivant_s',
  'acpassuran',
  {'paths': {'2': {'word_positions': [8]},
    '25': {'word_positions': [8]},
    '36': {'word_positions': [553, 148]},
    '37': {'word_positions': [8]},
    '5': {'word_positions': [8]},
    '7': {'word_positions': [8]}},
   'weight': 7}),
 ('ce_chômage',
  'cppcaisse',
  {'paths': {'2': {'word_positions': [11]},
    '25': {'word_positions': [11]},
    '36': {'word_positions': [556, 151]},
    '37': {'word_positions': [11]},
    '5': {'word_positions': [11]},
    '7': {'word_positions': [11]}},
   'weight': 7}),
 ('présente_dûment',
  'datée',
  {'paths': {'1': {'word_positions': [132]},
    '14': {'word_positions': [325, 150, 502]},
    '16': {'word_positions': [159]},
    '31': {'word_positions': [136]},
    '4': {'word_positions': [159]}},
   'weight': 7}),
 ('acpassuran',
  'ce_chômage',
  {'paths': {'2': {'word_positions': [9]},
    '25': {'word_positions': [9]},
    '36': {'word_positions': [554, 149]},
    '37': {'word_positions': [9]},
    '5': {'word_positions': [9]},
    '7': {'word_positions': [9]}},
   'weight': 7}),
 ('ircantec',
  'tranche_a',
  {'paths': {'13': {'word_positions': [206]},
    '20': {'word_positions': [216, 177]},
    '21': {'word_positions': [212]},
    '24': {'word_positions': [46]},
    '32': {'word_positions': [252, 206]}},
   'weight': 7}),
 ('saurions_gré',
  'de',
  {'paths': {'1': {'word_positions': [116]},
    '14': {'word_positions': [309, 134, 486]},
    '16': {'word_positions': [143]},
    '31': {'word_positions': [120]},
    '4': {'word_positions': [143]}},
   'weight': 7}),
 ('retour_de',
  'courrier_dans',
  {'paths': {'1': {'word_positions': [138]},
    '14': {'word_positions': [331, 156, 508]},
    '16': {'word_positions': [165]},
    '31': {'word_positions': [142]},
    '4': {'word_positions': [165]}},
   'weight': 7}),
 ('échéance',
  'de_votre',
  {'paths': {'1': {'word_positions': [100]},
    '14': {'word_positions': [95, 293, 470]},
    '16': {'word_positions': [104]},
    '31': {'word_positions': [104]},
    '4': {'word_positions': [104]}},
   'weight': 7}),
 ('de_travail',
  'a_été',
  {'paths': {'1': {'word_positions': [105]},
    '14': {'word_positions': [298, 475, 100]},
    '16': {'word_positions': [109]},
    '31': {'word_positions': [109]},
    '4': {'word_positions': [109]}},
   'weight': 7}),
 ('de_travail',
  'monsieur',
  {'paths': {'1': {'word_positions': [63]},
    '14': {'word_positions': [249, 42, 427]},
    '16': {'word_positions': [66]},
    '31': {'word_positions': [67]},
    '4': {'word_positions': [66]}},
   'weight': 7}),
 ('507_cotisation',
  'risque_cp',
  {'paths': {'36': {'word_positions': [118]},
    '37': {'word_positions': [321, 207]},
    '5': {'word_positions': [321, 207]},
    '7': {'word_positions': [327]}},
   'weight': 6}),
 ('plaisir',
  'de_vous',
  {'paths': {'1': {'word_positions': [91]},
    '14': {'word_positions': [284, 461]},
    '16': {'word_positions': [95]},
    '31': {'word_positions': [95]},
    '4': {'word_positions': [95]}},
   'weight': 6}),
 ('date_d',
  'édition',
  {'paths': {'2': {'word_positions': [62]},
    '25': {'word_positions': [62]},
    '29': {'word_positions': [52]},
    '37': {'word_positions': [62]},
    '5': {'word_positions': [62]},
    '7': {'word_positions': [62]}},
   'weight': 6}),
 ('an_p',
  'suvapassuran',
  {'paths': {'2': {'word_positions': [16]},
    '25': {'word_positions': [16]},
    '36': {'word_positions': [561]},
    '37': {'word_positions': [16]},
    '5': {'word_positions': [16]},
    '7': {'word_positions': [16]}},
   'weight': 6}),
 ('net',
  'à_payer',
  {'paths': {'2': {'word_positions': [330]},
    '25': {'word_positions': [324]},
    '36': {'word_positions': [131]},
    '37': {'word_positions': [334]},
    '5': {'word_positions': [334]},
    '7': {'word_positions': [340]}},
   'weight': 6}),
 ('emp_04',
  '16',
  {'paths': {'37': {'word_positions': [273, 261, 250, 299, 237, 286]}},
   'weight': 6}),
 ('7_724',
  '90',
  {'paths': {'37': {'word_positions': [338, 229, 344]},
    '5': {'word_positions': [338, 229, 344]}},
   'weight': 6}),
 ('du_miroir',
  'no_avs',
  {'paths': {'2': {'word_positions': [48]},
    '25': {'word_positions': [48]},
    '36': {'word_positions': [36]},
    '37': {'word_positions': [48]},
    '5': {'word_positions': [48]},
    '7': {'word_positions': [48]}},
   'weight': 6}),
 ('avons_le',
  'plaisir',
  {'paths': {'1': {'word_positions': [90]},
    '14': {'word_positions': [283, 460]},
    '16': {'word_positions': [94]},
    '31': {'word_positions': [94]},
    '4': {'word_positions': [94]}},
   'weight': 6}),
 ('7_565',
  '7_565',
  {'paths': {'29': {'word_positions': [207, 192, 203, 188, 205, 190]}},
   'weight': 6}),
 ('matricule_34696',
  '253_rue',
  {'paths': {'2': {'word_positions': [44]},
    '25': {'word_positions': [44]},
    '36': {'word_positions': [32]},
    '37': {'word_positions': [44]},
    '5': {'word_positions': [44]},
    '7': {'word_positions': [44]}},
   'weight': 6}),
 ('74200_thonon',
  'les_bains',
  {'paths': {'14': {'word_positions': [266]},
    '28': {'word_positions': [53]},
    '31': {'word_positions': [77]},
    '6': {'word_positions': [554]},
    '8': {'word_positions': [57, 87]}},
   'weight': 6}),
 ('nombre',
  'montant_total',
  {'paths': {'2': {'word_positions': [76]},
    '25': {'word_positions': [76]},
    '36': {'word_positions': [64]},
    '37': {'word_positions': [76]},
    '5': {'word_positions': [76]},
    '7': {'word_positions': [76]}},
   'weight': 6}),
 ('de_lausanne',
  'décompte',
  {'paths': {'2': {'word_positions': [33]},
    '25': {'word_positions': [33]},
    '36': {'word_positions': [21]},
    '37': {'word_positions': [33]},
    '5': {'word_positions': [33]},
    '7': {'word_positions': [33]}},
   'weight': 6}),
 ('benjamin_ricaud',
  'matricule_34696',
  {'paths': {'2': {'word_positions': [42]},
    '25': {'word_positions': [42]},
    '36': {'word_positions': [30]},
    '37': {'word_positions': [42]},
    '5': {'word_positions': [42]},
    '7': {'word_positions': [42]}},
   'weight': 6}),
 ('5600_57',
  'le_chalet',
  {'paths': {'2': {'word_positions': [54]},
    '25': {'word_positions': [54]},
    '36': {'word_positions': [42]},
    '37': {'word_positions': [54]},
    '5': {'word_positions': [54]},
    '7': {'word_positions': [54]}},
   'weight': 6}),
 ('employeur',
  'cotisation_avs',
  {'paths': {'2': {'word_positions': [229]},
    '25': {'word_positions': [223]},
    '36': {'word_positions': [404]},
    '37': {'word_positions': [233]},
    '5': {'word_positions': [233]},
    '7': {'word_positions': [239]}},
   'weight': 6}),
 ('de_rattachement',
  'nous',
  {'paths': {'1': {'word_positions': [87]},
    '14': {'word_positions': [83, 280]},
    '16': {'word_positions': [91]},
    '31': {'word_positions': [91]},
    '4': {'word_positions': [91]}},
   'weight': 6}),
 ('taux_base',
  'nombre',
  {'paths': {'2': {'word_positions': [75]},
    '25': {'word_positions': [75]},
    '36': {'word_positions': [63]},
    '37': {'word_positions': [75]},
    '5': {'word_positions': [75]},
    '7': {'word_positions': [75]}},
   'weight': 6}),
 ('allocation_familiale',
  'epe',
  {'paths': {'25': {'word_positions': [123, 102]},
    '29': {'word_positions': [73, 68]},
    '37': {'word_positions': [123, 102]}},
   'weight': 6}),
 ('charges_sociales',
  'employeur',
  {'paths': {'2': {'word_positions': [228]},
    '25': {'word_positions': [222]},
    '36': {'word_positions': [403]},
    '37': {'word_positions': [232]},
    '5': {'word_positions': [232]},
    '7': {'word_positions': [238]}},
   'weight': 6}),
 ('e_mail',
  'rh',
  {'paths': {'0': {'word_positions': [26]},
    '1': {'word_positions': [24]},
    '14': {'word_positions': [218]},
    '16': {'word_positions': [28]},
    '31': {'word_positions': [24]},
    '4': {'word_positions': [28]}},
   'weight': 6}),
 ('le_chalet',
  'centre_c0423',
  {'paths': {'2': {'word_positions': [56]},
    '25': {'word_positions': [56]},
    '36': {'word_positions': [44]},
    '37': {'word_positions': [56]},
    '5': {'word_positions': [56]},
    '7': {'word_positions': [56]}},
   'weight': 6}),
 ('ressources_humaines',
  'epfl_pl',
  {'paths': {'0': {'word_positions': [2]},
    '1': {'word_positions': [3]},
    '14': {'word_positions': [374]},
    '16': {'word_positions': [3]},
    '31': {'word_positions': [3]},
    '4': {'word_positions': [3]}},
   'weight': 6}),
 ('16',
  '7_680',
  {'paths': {'37': {'word_positions': [287, 274, 262, 300, 238]}},
   'weight': 5}),
 ('ph_avspassuran',
  'ce_vieillesse',
  {'paths': {'2': {'word_positions': [3]},
    '25': {'word_positions': [3]},
    '37': {'word_positions': [3]},
    '5': {'word_positions': [3]},
    '7': {'word_positions': [3]}},
   'weight': 5}),
 ('100_41',
  'h',
  {'paths': {'0': {'word_positions': [138, 132]},
    '14': {'word_positions': [673, 667]},
    '19': {'word_positions': [149]}},
   'weight': 5}),
 ('contract_of',
  'employment',
  {'paths': {'0': {'word_positions': [329, 50]},
    '14': {'word_positions': [865, 584]},
    '19': {'word_positions': [56]}},
   'weight': 5}),
 ('ce',
  'bulletin_de',
  {'paths': {'13': {'word_positions': [305]},
    '20': {'word_positions': [270]},
    '21': {'word_positions': [274]},
    '24': {'word_positions': [60]},
    '32': {'word_positions': [319]}},
   'weight': 5}),
 ('ce_accident',
  'bathvient_bi',
  {'paths': {'2': {'word_positions': [19]},
    '25': {'word_positions': [19]},
    '37': {'word_positions': [19]},
    '5': {'word_positions': [19]},
    '7': {'word_positions': [19]}},
   'weight': 5}),
 ('sur_proposition',
  'de_votre',
  {'paths': {'1': {'word_positions': [82]},
    '14': {'word_positions': [275]},
    '16': {'word_positions': [86]},
    '31': {'word_positions': [86]},
    '4': {'word_positions': [86]}},
   'weight': 5}),
 ('n_réf',
  'mw',
  {'paths': {'1': {'word_positions': [54]},
    '14': {'word_positions': [33, 418, 240]},
    '31': {'word_positions': [58]}},
   'weight': 5}),
 ('residence_prime',
  'specifique_paramed',
  {'paths': {'13': {'word_positions': [155]},
    '20': {'word_positions': [144]},
    '21': {'word_positions': [143]},
    '24': {'word_positions': [20]},
    '32': {'word_positions': [156]}},
   'weight': 5}),
 ('station7_ch',
  '1015_lausanne',
  {'paths': {'2': {'word_positions': [23]},
    '25': {'word_positions': [23]},
    '37': {'word_positions': [23]},
    '5': {'word_positions': [23]},
    '7': {'word_positions': [23]}},
   'weight': 5}),
 ('epfl_ch',
  'ecole_polytechnique',
  {'paths': {'2': {'word_positions': [28]},
    '25': {'word_positions': [28]},
    '37': {'word_positions': [28]},
    '5': {'word_positions': [28]},
    '7': {'word_positions': [28]}},
   'weight': 5}),
 ('bathvient_bi',
  'station7_ch',
  {'paths': {'2': {'word_positions': [21]},
    '25': {'word_positions': [21]},
    '37': {'word_positions': [21]},
    '5': {'word_positions': [21]},
    '7': {'word_positions': [21]}},
   'weight': 5}),
 ('14_7',
  '334_65',
  {'paths': {'25': {'word_positions': [265, 291, 253, 229, 278]}},
   'weight': 5}),
 ('emp_04',
  '14_7',
  {'paths': {'25': {'word_positions': [263, 251, 289, 227, 276]}},
   'weight': 5}),
 ('specifique_paramed',
  'prime_supplementaire',
  {'paths': {'13': {'word_positions': [157]},
    '20': {'word_positions': [146]},
    '21': {'word_positions': [145]},
    '24': {'word_positions': [22]},
    '32': {'word_positions': [158]}},
   'weight': 5}),
 ('s_s',
  'vieillesse_pat',
  {'paths': {'20': {'word_positions': [203]},
    '21': {'word_positions': [199, 189]},
    '32': {'word_positions': [242, 229]}},
   'weight': 5}),
 ('de_vous',
  'confirmer_que',
  {'paths': {'14': {'word_positions': [463, 286]},
    '16': {'word_positions': [97]},
    '31': {'word_positions': [97]},
    '4': {'word_positions': [97]}},
   'weight': 5}),
 ('montant_total',
  'salaire_mensuel',
  {'paths': {'2': {'word_positions': [78]},
    '25': {'word_positions': [78]},
    '37': {'word_positions': [78]},
    '5': {'word_positions': [78]},
    '7': {'word_positions': [78]}},
   'weight': 5}),
 ('désignation_période',
  'taux_base',
  {'paths': {'2': {'word_positions': [73]},
    '25': {'word_positions': [73]},
    '37': {'word_positions': [73]},
    '5': {'word_positions': [73]},
    '7': {'word_positions': [73]}},
   'weight': 5}),
 ('page_1',
  'désignation_période',
  {'paths': {'2': {'word_positions': [71]},
    '25': {'word_positions': [71]},
    '37': {'word_positions': [71]},
    '5': {'word_positions': [71]},
    '7': {'word_positions': [71]}},
   'weight': 5}),
 ('bi',
  'a1_407',
  {'paths': {'1': {'word_positions': [11]},
    '14': {'word_positions': [7]},
    '16': {'word_positions': [15]},
    '31': {'word_positions': [11]},
    '4': {'word_positions': [15]}},
   'weight': 5}),
 ('de_votre',
  'unité',
  {'paths': {'1': {'word_positions': [84]},
    '14': {'word_positions': [277]},
    '16': {'word_positions': [88]},
    '31': {'word_positions': [88]},
    '4': {'word_positions': [88]}},
   'weight': 5}),
 ('fct',
  '7_echelon',
  {'paths': {'2': {'word_positions': [67]},
    '36': {'word_positions': [55, 215]},
    '5': {'word_positions': [67]},
    '7': {'word_positions': [67]}},
   'weight': 5}),
 ('2_760',
  '00_anthonin',
  {'paths': {'2': {'word_positions': [102]},
    '25': {'word_positions': [96]},
    '37': {'word_positions': [96]},
    '5': {'word_positions': [96]},
    '7': {'word_positions': [102]}},
   'weight': 5}),
 ('2_760',
  '00_maya',
  {'paths': {'2': {'word_positions': [123]},
    '25': {'word_positions': [117]},
    '37': {'word_positions': [117]},
    '5': {'word_positions': [117]},
    '7': {'word_positions': [123]}},
   'weight': 5}),
 ('74500_maxilly',
  'sur_léman',
  {'paths': {'1': {'word_positions': [73]},
    '14': {'word_positions': [444, 70]},
    '16': {'word_positions': [77]},
    '4': {'word_positions': [77]}},
   'weight': 5}),
 ('unité',
  'de_rattachement',
  {'paths': {'1': {'word_positions': [85]},
    '14': {'word_positions': [278]},
    '16': {'word_positions': [89]},
    '31': {'word_positions': [89]},
    '4': {'word_positions': [89]}},
   'weight': 5}),
 ('bulletin_de',
  'paie_sans',
  {'paths': {'13': {'word_positions': [307]},
    '20': {'word_positions': [272]},
    '21': {'word_positions': [276]},
    '24': {'word_positions': [62]},
    '32': {'word_positions': [321]}},
   'weight': 5}),
 ('15',
  '7_565',
  {'paths': {'36': {'word_positions': [97, 84, 424, 71, 409]}}, 'weight': 5}),
 ('à_ce',
  'que_ces',
  {'paths': {'11': {'word_positions': [418, 397]},
    '15': {'word_positions': [299, 278]},
    '34': {'word_positions': [405]}},
   'weight': 5}),
 ('7_334',
  '65',
  {'paths': {'2': {'word_positions': [89]},
    '25': {'word_positions': [89, 155, 179, 144]}},
   'weight': 5}),
 ('sur_léman',
  'lausanne_le',
  {'paths': {'1': {'word_positions': [75]},
    '14': {'word_positions': [446, 72]},
    '16': {'word_positions': [79]},
    '4': {'word_positions': [79]}},
   'weight': 5}),
 ('confirmer_que',
  'la_nouvelle',
  {'paths': {'14': {'word_positions': [465, 288]},
    '16': {'word_positions': [99]},
    '31': {'word_positions': [99]},
    '4': {'word_positions': [99]}},
   'weight': 5}),
 ('00_anthonin',
  '230_00',
  {'paths': {'2': {'word_positions': [104]},
    '25': {'word_positions': [98]},
    '37': {'word_positions': [98]},
    '5': {'word_positions': [98]},
    '7': {'word_positions': [104]}},
   'weight': 5}),
 ('ressources_humaines',
  'ph_avspassuran',
  {'paths': {'2': {'word_positions': [1]},
    '25': {'word_positions': [1]},
    '37': {'word_positions': [1]},
    '5': {'word_positions': [1]},
    '7': {'word_positions': [1]}},
   'weight': 5}),
 ('00_maya',
  '230_00',
  {'paths': {'2': {'word_positions': [125]},
    '25': {'word_positions': [119]},
    '37': {'word_positions': [119]},
    '5': {'word_positions': [119]},
    '7': {'word_positions': [125]}},
   'weight': 5}),
 ('de_salaire',
  'avril',
  {'paths': {'25': {'word_positions': [36]},
    '36': {'word_positions': [196, 24]},
    '37': {'word_positions': [36]}},
   'weight': 4}),
 ('11',
  '05_2015',
  {'paths': {'2': {'word_positions': [64]},
    '25': {'word_positions': [64]},
    '36': {'word_positions': [52, 212]}},
   'weight': 4}),
 ('que_ces',
  'données',
  {'paths': {'11': {'word_positions': [420, 399]},
    '15': {'word_positions': [301, 280]}},
   'weight': 4}),
 ('données',
  'personnelles_vous',
  {'paths': {'11': {'word_positions': [368, 384]},
    '15': {'word_positions': [265, 250]}},
   'weight': 4}),
 ('c_s',
  'g_deductible',
  {'paths': {'13': {'word_positions': [192]},
    '20': {'word_positions': [169]},
    '21': {'word_positions': [169]},
    '32': {'word_positions': [194]}},
   'weight': 4}),
 ('84',
  '507_cotisation',
  {'paths': {'37': {'word_positions': [169, 268]},
    '5': {'word_positions': [169, 268]}},
   'weight': 4}),
 ('7_945',
  '85_0',
  {'paths': {'2': {'word_positions': [298, 185, 285, 173]}}, 'weight': 4}),
 ('cumul_du',
  'temps_travaille',
  {'paths': {'13': {'word_positions': [258]},
    '20': {'word_positions': [221]},
    '21': {'word_positions': [217]},
    '32': {'word_positions': [258]}},
   'weight': 4}),
 ('n_30003',
  '01438_00051598994',
  {'paths': {'6': {'word_positions': [643, 20, 301, 524]}}, 'weight': 4}),
 ('à_la',
  'base',
  {'paths': {'8': {'word_positions': [345, 449, 477, 382]}}, 'weight': 4}),
 ('date_valeur',
  'nature',
  {'paths': {'6': {'word_positions': [657, 122, 295]},
    '9': {'word_positions': [90]}},
   'weight': 4}),
 ('g',
  'non_deductible',
  {'paths': {'13': {'word_positions': [200]},
    '20': {'word_positions': [174]},
    '21': {'word_positions': [174]},
    '32': {'word_positions': [201]}},
   'weight': 4}),
 ('indte_speciale',
  'sujetion',
  {'paths': {'13': {'word_positions': [169]},
    '20': {'word_positions': [155]},
    '21': {'word_positions': [154]},
    '32': {'word_positions': [170]}},
   'weight': 4}),
 ('groupe',
  'société_générale',
  {'paths': {'11': {'word_positions': [426, 334]},
    '15': {'word_positions': [217]},
    '34': {'word_positions': [412]}},
   'weight': 4}),
 ('12_15',
  '73_675',
  {'paths': {'7': {'word_positions': [319, 217, 332, 205]}}, 'weight': 4}),
 ('mes_nos',
  'comptes',
  {'paths': {'11': {'word_positions': [105, 78]},
    '15': {'word_positions': [109, 80]}},
   'weight': 4}),
 ('montant',
  'de_votre',
  {'paths': {'6': {'word_positions': [844]},
    '8': {'word_positions': [695, 179, 173]}},
   'weight': 4}),
 ('agence_thonon',
  'les_bains',
  {'paths': {'6': {'word_positions': [577, 51]},
    '9': {'word_positions': [249, 27]}},
   'weight': 4}),
 ('epfl_ch',
  'f_e',
  {'paths': {'1': {'word_positions': [27]},
    '16': {'word_positions': [31]},
    '31': {'word_positions': [27]},
    '4': {'word_positions': [31]}},
   'weight': 4}),
 ('cotisation_avs',
  'emp',
  {'paths': {'2': {'word_positions': [231]},
    '29': {'word_positions': [108]},
    '5': {'word_positions': [235]},
    '7': {'word_positions': [241]}},
   'weight': 4}),
 ('http_rh',
  'epfl_ch',
  {'paths': {'1': {'word_positions': [43]},
    '14': {'word_positions': [228, 53]},
    '31': {'word_positions': [47]}},
   'weight': 4}),
 ('trait',
  'hos_indemnite',
  {'paths': {'13': {'word_positions': [151]},
    '20': {'word_positions': [140]},
    '21': {'word_positions': [139]},
    '32': {'word_positions': [152]}},
   'weight': 4}),
 ('04_15',
  '7_565',
  {'paths': {'36': {'word_positions': [351, 344, 331, 337]}}, 'weight': 4}),
 ('f7745oo_maxilly7sur7leman',
  'date_d',
  {'paths': {'36': {'word_positions': [48]},
    '37': {'word_positions': [60]},
    '5': {'word_positions': [60]},
    '7': {'word_positions': [60]}},
   'weight': 4}),
 ('travail',
  'p_deplaf',
  {'paths': {'13': {'word_positions': [216]},
    '20': {'word_positions': [209]},
    '21': {'word_positions': [205]},
    '32': {'word_positions': [217]}},
   'weight': 4}),
 ('8_195',
  '85',
  {'paths': {'7': {'word_positions': [246, 171, 270, 160]}}, 'weight': 4}),
 ('8_195',
  '85_0',
  {'paths': {'7': {'word_positions': [195, 295, 183, 308]}}, 'weight': 4}),
 ('fr',
  '74500_maxilly',
  {'paths': {'1': {'word_positions': [71]},
    '14': {'word_positions': [68]},
    '16': {'word_positions': [75]},
    '4': {'word_positions': [75]}},
   'weight': 4}),
 ('ss_accid',
  'travail',
  {'paths': {'13': {'word_positions': [215]},
    '20': {'word_positions': [208]},
    '21': {'word_positions': [204]},
    '32': {'word_positions': [216]}},
   'weight': 4}),
 ('08_16',
  '75_175',
  {'paths': {'5': {'word_positions': [199, 313, 211, 326]}}, 'weight': 4}),
 ('du_miroir',
  'fr',
  {'paths': {'1': {'word_positions': [70]},
    '14': {'word_positions': [67]},
    '16': {'word_positions': [74]},
    '4': {'word_positions': [74]}},
   'weight': 4}),
 ('relevé',
  'de_compte',
  {'paths': {'6': {'word_positions': [2, 633, 286]},
    '9': {'word_positions': [222]}},
   'weight': 4}),
 ('taxe_d',
  'habitation',
  {'paths': {'8': {'word_positions': [177, 250, 12, 314]}}, 'weight': 4}),
 ('7_565',
  'cotisation',
  {'paths': {'36': {'word_positions': [353, 346, 411, 339]}}, 'weight': 4}),
 ('7_565',
  '40',
  {'paths': {'36': {'word_positions': [99, 86, 73]},
    '7': {'word_positions': [89]}},
   'weight': 4}),
 ('cat_taux',
  '1',
  {'paths': {'13': {'word_positions': [163]},
    '20': {'word_positions': [152]},
    '21': {'word_positions': [151]},
    '32': {'word_positions': [164]}},
   'weight': 4}),
 ('les_rapports',
  'de_travail',
  {'paths': {'0': {'word_positions': [379, 391]},
    '14': {'word_positions': [915, 927]}},
   'weight': 4}),
 ('prime_supplementaire',
  'prime_2eme',
  {'paths': {'13': {'word_positions': [159]},
    '20': {'word_positions': [148]},
    '21': {'word_positions': [147]},
    '32': {'word_positions': [160]}},
   'weight': 4}),
 ('prime_2eme',
  'cat_taux',
  {'paths': {'13': {'word_positions': [161]},
    '20': {'word_positions': [150]},
    '21': {'word_positions': [149]},
    '32': {'word_positions': [162]}},
   'weight': 4}),
 ('rale_de',
  'lausan_n',
  {'paths': {'1': {'word_positions': [33]},
    '16': {'word_positions': [36]},
    '19': {'word_positions': [35]},
    '4': {'word_positions': [36]}},
   'weight': 4}),
 ('fonds',
  'emploi_hospit',
  {'paths': {'13': {'word_positions': [246]},
    '20': {'word_positions': [212]},
    '21': {'word_positions': [208]},
    '32': {'word_positions': [247]}},
   'weight': 4}),
 ('tél',
  '04_50',
  {'paths': {'11': {'word_positions': [48]},
    '15': {'word_positions': [50]},
    '34': {'word_positions': [47]},
    '8': {'word_positions': [699]}},
   'weight': 4}),
 ('l_epfl',
  'm_wannier',
  {'paths': {'1': {'word_positions': [153]},
    '14': {'word_positions': [346, 523]},
    '31': {'word_positions': [157]}},
   'weight': 4}),
 ('00_00',
  '01_001',
  {'paths': {'13': {'word_positions': [134]},
    '20': {'word_positions': [131]},
    '21': {'word_positions': [124]},
    '32': {'word_positions': [131]}},
   'weight': 4}),
 ('cotisation',
  'risque_cp',
  {'paths': {'2': {'word_positions': [203]},
    '25': {'word_positions': [197]},
    '29': {'word_positions': [91]},
    '36': {'word_positions': [361]}},
   'weight': 4}),
 ('hos_indemnite',
  'residence_prime',
  {'paths': {'13': {'word_positions': [153]},
    '20': {'word_positions': [142]},
    '21': {'word_positions': [141]},
    '32': {'word_positions': [154]}},
   'weight': 4}),
 ('emploi_hospit',
  'p',
  {'paths': {'13': {'word_positions': [248]},
    '20': {'word_positions': [214]},
    '21': {'word_positions': [210]},
    '32': {'word_positions': [249]}},
   'weight': 4}),
 ('particulier',
  'en_euros',
  {'paths': {'6': {'word_positions': [7, 520, 639, 291]}}, 'weight': 4}),
 ('base_pl',
  'trait',
  {'paths': {'13': {'word_positions': [150]},
    '20': {'word_positions': [139]},
    '21': {'word_positions': [138]},
    '32': {'word_positions': [151]}},
   'weight': 4}),
 ('04_14',
  '7_334',
  {'paths': {'25': {'word_positions': [153, 177, 165, 142]}}, 'weight': 4}),
 ('epfl_pl',
  'rh',
  {'paths': {'0': {'word_positions': [4]},
    '19': {'word_positions': [6]},
    '22': {'word_positions': [6]},
    '26': {'word_positions': [6]}},
   'weight': 4}),
 ('7_680',
  '80_5',
  {'paths': {'37': {'word_positions': [240, 154]},
    '5': {'word_positions': [240, 154]}},
   'weight': 4}),
 ('site_web',
  'http_rh',
  {'paths': {'1': {'word_positions': [41]},
    '14': {'word_positions': [226, 405]},
    '31': {'word_positions': [45]}},
   'weight': 4}),
 ('34696_modification',
  'de_votre',
  {'paths': {'1': {'word_positions': [58]},
    '14': {'word_positions': [244]},
    '16': {'word_positions': [61]},
    '4': {'word_positions': [61]}},
   'weight': 4}),
 ('lausan_n',
  'e_ch',
  {'paths': {'1': {'word_positions': [35]},
    '16': {'word_positions': [38]},
    '19': {'word_positions': [37]},
    '4': {'word_positions': [38]}},
   'weight': 4}),
 ('sur_le',
  'personnel',
  {'paths': {'0': {'word_positions': [353, 368]},
    '14': {'word_positions': [889, 904]}},
   'weight': 4}),
 ('centre_c0423',
  'f7745oo_maxilly7sur7leman',
  {'paths': {'36': {'word_positions': [46]},
    '37': {'word_positions': [58]},
    '5': {'word_positions': [58]},
    '7': {'word_positions': [58]}},
   'weight': 4}),
 ('risque_cp',
  'emp',
  {'paths': {'2': {'word_positions': [319]},
    '29': {'word_positions': [127]},
    '5': {'word_positions': [323]},
    '7': {'word_positions': [329]}},
   'weight': 4}),
 ('fax',
  '4121_693',
  {'paths': {'0': {'word_positions': [18]},
    '1': {'word_positions': [16]},
    '14': {'word_positions': [210, 389]}},
   'weight': 4}),
 ('vieillesse_pat',
  'plaf',
  {'paths': {'13': {'word_positions': [230]},
    '20': {'word_positions': [195]},
    '21': {'word_positions': [191]},
    '32': {'word_positions': [231]}},
   'weight': 4}),
 ('au_capital',
  'de',
  {'paths': {'11': {'word_positions': [486]},
    '15': {'word_positions': [366]},
    '34': {'word_positions': [469]},
    '9': {'word_positions': [435]}},
   'weight': 4}),
 ('directive_sur',
  'les_rapports',
  {'paths': {'0': {'word_positions': [377, 389]},
    '14': {'word_positions': [913, 925]}},
   'weight': 4}),
 ('a1_407',
  'bâtiment_bi',
  {'paths': {'1': {'word_positions': [13]},
    '14': {'word_positions': [207, 9, 385]}},
   'weight': 4}),
 ('compte_de',
  'particulier',
  {'paths': {'6': {'word_positions': [290, 6, 519, 638]}}, 'weight': 4}),
 ('envoi_n',
  '8_page',
  {'paths': {'6': {'word_positions': [652, 534, 311]},
    '9': {'word_positions': [301]}},
   'weight': 4}),
 ('d_assurance',
  'avs_al',
  {'paths': {'22': {'word_positions': [35, 52]},
    '26': {'word_positions': [35, 52]}},
   'weight': 4}),
 ('tranche_a',
  'p',
  {'paths': {'20': {'word_positions': [218]},
    '21': {'word_positions': [214]},
    '24': {'word_positions': [48]},
    '32': {'word_positions': [254]}},
   'weight': 4}),
 ('12_14',
  '70_780',
  {'paths': {'2': {'word_positions': [207, 322, 195, 309]}}, 'weight': 4}),
 ('552_120',
  '222_rcs',
  {'paths': {'6': {'word_positions': [620, 926]},
    '9': {'word_positions': [199, 428]}},
   'weight': 4}),
 ('00_anthonin',
  '139',
  {'paths': {'2': {'word_positions': [115]},
    '25': {'word_positions': [109]},
    '37': {'word_positions': [109]},
    '7': {'word_positions': [115]}},
   'weight': 4}),
 ('04_50',
  '81_99',
  {'paths': {'6': {'word_positions': [64]},
    '9': {'word_positions': [279, 261, 54]}},
   'weight': 4}),
 ('de_travail',
  'des',
  {'paths': {'0': {'word_positions': [393, 381]},
    '14': {'word_positions': [917, 929]}},
   'weight': 4}),
 ('e_ch',
  '1015_lausanne',
  {'paths': {'1': {'word_positions': [37]},
    '16': {'word_positions': [40]},
    '19': {'word_positions': [39]},
    '4': {'word_positions': [40]}},
   'weight': 4}),
 ('04_16',
  '7_680',
  {'paths': {'37': {'word_positions': [175, 163, 152, 187]}}, 'weight': 4}),
 ('13_07',
  '1979',
  {'paths': {'0': {'word_positions': [71]},
    '14': {'word_positions': [605]},
    '22': {'word_positions': [223]},
    '26': {'word_positions': [224]}},
   'weight': 4}),
 ('entre_between',
  'l',
  {'paths': {'0': {'word_positions': [53]},
    '14': {'word_positions': [587]},
    '19': {'word_positions': [61]}},
   'weight': 3}),
 ('indicative',
  '1_euro',
  {'paths': {'6': {'word_positions': [115]},
    '9': {'word_positions': [323, 83]}},
   'weight': 3}),
 ('net_a',
  'payer',
  {'paths': {'20': {'word_positions': [263]},
    '21': {'word_positions': [243]},
    '32': {'word_positions': [275]}},
   'weight': 3}),
 ('00',
  '0_75',
  {'paths': {'37': {'word_positions': [214]},
    '5': {'word_positions': [214]},
    '7': {'word_positions': [220]}},
   'weight': 3}),
 ('ect',
  '7_echelon',
  {'paths': {'25': {'word_positions': [67]},
    '29': {'word_positions': [57]},
    '37': {'word_positions': [67]}},
   'weight': 3}),
 ('fonction',
  'collaborateur_scientifique',
  {'paths': {'0': {'word_positions': [88]},
    '14': {'word_positions': [622]},
    '19': {'word_positions': [104]}},
   'weight': 3}),
 ('85',
  '5_1500',
  {'paths': {'2': {'word_positions': [151]},
    '7': {'word_positions': [247, 161]}},
   'weight': 3}),
 ('annuel_brut',
  'chf_91',
  {'paths': {'0': {'word_positions': [146]},
    '14': {'word_positions': [681]},
    '19': {'word_positions': [163]}},
   'weight': 3}),
 ('date_de',
  'naissance',
  {'paths': {'0': {'word_positions': [68]},
    '14': {'word_positions': [602]},
    '19': {'word_positions': [83]}},
   'weight': 3}),
 ('ces',
  'transferts_de',
  {'paths': {'11': {'word_positions': [352]},
    '15': {'word_positions': [235]},
    '34': {'word_positions': [341]}},
   'weight': 3}),
 ('ces',
  'finalités_être',
  {'paths': {'11': {'word_positions': [327]},
    '15': {'word_positions': [210]},
    '34': {'word_positions': [317]}},
   'weight': 3}),
 ('ladite_agence',
  'toutes_les',
  {'paths': {'11': {'word_positions': [96]},
    '15': {'word_positions': [100]},
    '34': {'word_positions': [95]}},
   'weight': 3}),
 ('afaallocations',
  'fam_liales',
  {'paths': {'2': {'word_positions': [342]},
    '5': {'word_positions': [346]},
    '7': {'word_positions': [352]}},
   'weight': 3}),
 ('la_protection',
  'de_vos',
  {'paths': {'11': {'word_positions': [365]},
    '15': {'word_positions': [247]},
    '34': {'word_positions': [352]}},
   'weight': 3}),
 ('professeur_pierre',
  'vandergheynst_pour',
  {'paths': {'0': {'word_positions': [265]},
    '14': {'word_positions': [800]},
    '19': {'word_positions': [279]}},
   'weight': 3}),
 ('rebecca',
  'urssaf_herault',
  {'paths': {'13': {'word_positions': [41]},
    '21': {'word_positions': [26]},
    '32': {'word_positions': [35]}},
   'weight': 3}),
 ('sans_motif',
  'vous_opposer',
  {'paths': {'11': {'word_positions': [414]},
    '15': {'word_positions': [295]},
    '34': {'word_positions': [401]}},
   'weight': 3}),
 ('sans_frais',
  'et',
  {'paths': {'11': {'word_positions': [411]},
    '15': {'word_positions': [292]},
    '34': {'word_positions': [398]}},
   'weight': 3}),
 ('frais_avs',
  'emp_04',
  {'paths': {'25': {'word_positions': [238]},
    '36': {'word_positions': [414]},
    '37': {'word_positions': [248]}},
   'weight': 3}),
 ('droit',
  'd_accès',
  {'paths': {'11': {'word_positions': [374]},
    '15': {'word_positions': [256]},
    '34': {'word_positions': [361]}},
   'weight': 3}),
 ('2012',
  'contrat',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [45]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [579]},
    '19': {'text_data': {'length': 385},
     'text_id': 19,
     'word_positions': [51]}},
   'weight': 3}),
 ('c_s',
  'g',
  {'paths': {'20': {'word_positions': [173]},
    '21': {'word_positions': [173]},
    '32': {'word_positions': [200]}},
   'weight': 3}),
 ('aider_a',
  'faire_valoir',
  {'paths': {'13': {'word_positions': [298]},
    '21': {'word_positions': [268]},
    '32': {'word_positions': [313]}},
   'weight': 3}),
 ('pour_des',
  'besoins',
  {'paths': {'11': {'word_positions': [301]},
    '15': {'word_positions': [184]},
    '34': {'word_positions': [291]}},
   'weight': 3}),
 ('special_clauses',
  'ce',
  {'paths': {'0': {'word_positions': [242]},
    '14': {'word_positions': [777]},
    '19': {'word_positions': [256]}},
   'weight': 3}),
 ('7_945',
  '85',
  {'paths': {'2': {'word_positions': [161, 260, 150]}}, 'weight': 3}),
 ('besoins',
  'de_gestion',
  {'paths': {'11': {'word_positions': [302]},
    '15': {'word_positions': [185]},
    '34': {'word_positions': [292]}},
   'weight': 3}),
 ('définitivement_fin',
  'à_la',
  {'paths': {'14': {'word_positions': [126]},
    '16': {'word_positions': [135]},
    '4': {'word_positions': [135]}},
   'weight': 3}),
 ('ou',
  'en_dehors',
  {'paths': {'11': {'word_positions': [345]},
    '15': {'word_positions': [228]},
    '34': {'word_positions': [334]}},
   'weight': 3}),
 ('de_gestion',
  'de_la',
  {'paths': {'11': {'word_positions': [304]},
    '15': {'word_positions': [187]},
    '34': {'word_positions': [294]}},
   'weight': 3}),
 ('30_09',
  '2013',
  {'paths': {'0': {'word_positions': [111]},
    '19': {'word_positions': [127]},
    '8': {'word_positions': [152]}},
   'weight': 3}),
 ('à_la',
  'date_précitée',
  {'paths': {'14': {'word_positions': [128]},
    '16': {'word_positions': [137]},
    '4': {'word_positions': [137]}},
   'weight': 3}),
 ('epfl_et',
  'and',
  {'paths': {'0': {'word_positions': [61]},
    '14': {'word_positions': [595]},
    '19': {'word_positions': [69]}},
   'weight': 3}),
 ('cot_périodique',
  'cp_emp',
  {'paths': {'2': {'word_positions': [305]},
    '5': {'word_positions': [309]},
    '7': {'word_positions': [315]}},
   'weight': 3}),
 ('av',
  'doyen_gaston',
  {'paths': {'13': {'word_positions': [30]},
    '21': {'word_positions': [17]},
    '32': {'word_positions': [25]}},
   'weight': 3}),
 ('paie_sans',
  'limitation',
  {'paths': {'13': {'word_positions': [309]},
    '20': {'word_positions': [274]},
    '21': {'word_positions': [278]}},
   'weight': 3}),
 ('100_salaire',
  'annuel_brut',
  {'paths': {'0': {'word_positions': [144]},
    '14': {'word_positions': [679]},
    '19': {'word_positions': [161]}},
   'weight': 3}),
 ('8_208',
  '60',
  {'paths': {'7': {'word_positions': [235, 350, 344]}}, 'weight': 3}),
 ('du_contrat',
  '01_10',
  {'paths': {'0': {'word_positions': [103]},
    '14': {'word_positions': [637]},
    '19': {'word_positions': [119]}},
   'weight': 3}),
 ('du_contrat',
  '30_09',
  {'paths': {'0': {'word_positions': [109]},
    '14': {'word_positions': [643]},
    '19': {'word_positions': [125]}},
   'weight': 3}),
 ('période',
  'd_essai',
  {'paths': {'0': {'word_positions': [113]},
    '14': {'word_positions': [648]},
    '19': {'word_positions': [129]}},
   'weight': 3}),
 ('de',
  '1',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [269, 610]},
    '9': {'text_data': {'length': 451},
     'text_id': 9,
     'word_positions': [436]}},
   'weight': 3}),
 ('de',
  'prospection',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [432]},
    '15': {'text_data': {'length': 388},
     'text_id': 15,
     'word_positions': [314]},
    '34': {'text_data': {'length': 490},
     'text_id': 34,
     'word_positions': [418]}},
   'weight': 3}),
 ('de',
  'séjour',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [255]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [790]},
    '19': {'text_data': {'length': 385},
     'text_id': 19,
     'word_positions': [270]}},
   'weight': 3}),
 ('de',
  'suppression',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [379]},
    '15': {'text_data': {'length': 388},
     'text_id': 15,
     'word_positions': [261]},
    '34': {'text_data': {'length': 490},
     'text_id': 34,
     'word_positions': [366]}},
   'weight': 3}),
 ('de',
  '9_380',
  {'paths': {'11': {'word_positions': [487]},
    '15': {'word_positions': [367]},
    '34': {'word_positions': [470]}},
   'weight': 3}),
 ('enjamin',
  'ricaud_date',
  {'paths': {'16': {'word_positions': [188]},
    '31': {'word_positions': [167]},
    '4': {'word_positions': [188]}},
   'weight': 3}),
 ('70_780',
  '00',
  {'paths': {'2': {'word_positions': [209, 311]},
    '25': {'word_positions': [203]}},
   'weight': 3}),
 ('exécution_de',
  'ces',
  {'paths': {'11': {'word_positions': [326]},
    '15': {'word_positions': [209]},
    '34': {'word_positions': [316]}},
   'weight': 3}),
 ('l',
  'ecole_polytechnique',
  {'paths': {'0': {'word_positions': [54]},
    '14': {'word_positions': [588]},
    '19': {'word_positions': [62]}},
   'weight': 3}),
 ('returned_to',
  'hr_department',
  {'paths': {'0': {'word_positions': [315]},
    '14': {'word_positions': [851]},
    '19': {'word_positions': [333]}},
   'weight': 3}),
 ('cotisation_ap',
  'suva_emp',
  {'paths': {'2': {'word_positions': [292]},
    '5': {'word_positions': [296]},
    '7': {'word_positions': [302]}},
   'weight': 3}),
 ('périodique_cp',
  'emp_04',
  {'paths': {'25': {'word_positions': [300]},
    '36': {'word_positions': [107]},
    '37': {'word_positions': [310]}},
   'weight': 3}),
 ('81_99',
  '00',
  {'paths': {'6': {'word_positions': [66]},
    '9': {'word_positions': [41, 263]}},
   'weight': 3}),
 ('lausanne',
  'july_25',
  {'paths': {'0': {'word_positions': [42]},
    '14': {'word_positions': [576]},
    '19': {'word_positions': [48]}},
   'weight': 3}),
 ('ricaud_benjamin',
  'date_de',
  {'paths': {'0': {'word_positions': [66]},
    '14': {'word_positions': [600]},
    '19': {'word_positions': [81]}},
   'weight': 3}),
 ('aussi',
  'sans_frais',
  {'paths': {'11': {'word_positions': [409]},
    '15': {'word_positions': [290]},
    '34': {'word_positions': [396]}},
   'weight': 3}),
 ('qu',
  'il_s',
  {'paths': {'14': {'word_positions': [110]},
    '16': {'word_positions': [119]},
    '4': {'word_positions': [119]}},
   'weight': 3}),
 ('les_bains',
  'tél',
  {'paths': {'11': {'word_positions': [47]},
    '15': {'word_positions': [49]},
    '34': {'word_positions': [46]}},
   'weight': 3}),
 ('pour_motif',
  'légitime',
  {'paths': {'11': {'word_positions': [394]},
    '15': {'word_positions': [275]},
    '34': {'word_positions': [381]}},
   'weight': 3}),
 ('signaux_2',
  'reporting',
  {'paths': {'0': {'word_positions': [98]},
    '14': {'word_positions': [632]},
    '19': {'word_positions': [114]}},
   'weight': 3}),
 ('address_fr',
  '13011',
  {'paths': {'0': {'word_positions': [84]},
    '14': {'word_positions': [618]},
    '19': {'word_positions': [100]}},
   'weight': 3}),
 ('contacts',
  'votre_banque',
  {'paths': {'6': {'word_positions': [11]},
    '9': {'word_positions': [10, 230]}},
   'weight': 3}),
 ('date_probation',
  'period_3',
  {'paths': {'0': {'word_positions': [122]},
    '14': {'word_positions': [657]},
    '19': {'word_positions': [138]}},
   'weight': 3}),
 ('postfinance',
  'sa_ch5609000000124743854',
  {'paths': {'2': {'word_positions': [336]},
    '36': {'word_positions': [137]},
    '7': {'word_positions': [346]}},
   'weight': 3}),
 ('opérations',
  'sans_exception',
  {'paths': {'11': {'word_positions': [99]},
    '15': {'word_positions': [103]},
    '34': {'word_positions': [98]}},
   'weight': 3}),
 ('60',
  'allocation_enfant',
  {'paths': {'37': {'word_positions': [111]},
    '5': {'word_positions': [111]},
    '7': {'word_positions': [117]}},
   'weight': 3}),
 ('vous_pouvez',
  'aussi',
  {'paths': {'11': {'word_positions': [408]},
    '15': {'word_positions': [289]},
    '34': {'word_positions': [395]}},
   'weight': 3}),
 ('votre_banque',
  'à',
  {'paths': {'6': {'word_positions': [13]},
    '9': {'word_positions': [12, 232]}},
   'weight': 3}),
 ('publica',
  'pension_fund',
  {'paths': {'0': {'word_positions': [200]},
    '14': {'word_positions': [735]},
    '19': {'word_positions': [214]}},
   'weight': 3}),
 ('ci',
  'contre__',
  {'paths': {'11': {'word_positions': [439]},
    '15': {'word_positions': [321]},
    '34': {'word_positions': [425]}},
   'weight': 3}),
 ('légitime',
  'à_ce',
  {'paths': {'11': {'word_positions': [395]},
    '15': {'word_positions': [276]},
    '34': {'word_positions': [382]}},
   'weight': 3}),
 ('vos',
  'contacts',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [10]},
    '9': {'text_data': {'length': 451},
     'text_id': 9,
     'word_positions': [9, 229]}},
   'weight': 3}),
 ('2016_nom',
  'et_adresse',
  {'paths': {'11': {'word_positions': [17]},
    '15': {'word_positions': [17]},
    '34': {'word_positions': [16]}},
   'weight': 3}),
 ('vous_opposer',
  'à_ce',
  {'paths': {'11': {'word_positions': [416]},
    '15': {'word_positions': [297]},
    '34': {'word_positions': [403]}},
   'weight': 3}),
 ('vous_opposer',
  'pour_motif',
  {'paths': {'11': {'word_positions': [392]},
    '15': {'word_positions': [273]},
    '34': {'word_positions': [379]}},
   'weight': 3}),
 ('du_2310812015',
  'au_2210912015',
  {'paths': {'6': {'word_positions': [25, 808, 648]}}, 'weight': 3}),
 ('emp',
  '08_16',
  {'paths': {'5': {'word_positions': [260, 324, 236]}}, 'weight': 3}),
 ('emp',
  '12_14',
  {'paths': {'2': {'word_positions': [256, 320, 232]}}, 'weight': 3}),
 ('emp',
  '12_15',
  {'paths': {'7': {'word_positions': [266, 330, 242]}}, 'weight': 3}),
 ('societe_generale',
  'relevé',
  {'paths': {'6': {'word_positions': [1, 285]},
    '9': {'word_positions': [221]}},
   'weight': 3}),
 ('1_av',
  'jean_leger',
  {'paths': {'11': {'word_positions': [55]},
    '15': {'word_positions': [57]},
    '34': {'word_positions': [54]}},
   'weight': 3}),
 ('bulletin',
  'de_salaire',
  {'paths': {'20': {'word_positions': [9]},
    '21': {'word_positions': [6]},
    '24': {'word_positions': [0]}},
   'weight': 3}),
 ('bâtiment',
  'bl_fax',
  {'paths': {'16': {'word_positions': [18]},
    '31': {'word_positions': [14]},
    '4': {'word_positions': [18]}},
   'weight': 3}),
 ('s_et',
  'ou_la',
  {'paths': {'11': {'word_positions': [287]},
    '15': {'word_positions': [170]},
    '34': {'word_positions': [277]}},
   'weight': 3}),
 ('afpallocations',
  'fam_liales',
  {'paths': {'25': {'word_positions': [336]},
    '36': {'word_positions': [159]},
    '37': {'word_positions': [346]}},
   'weight': 3}),
 ('matricule',
  '01',
  {'paths': {'13': {'text_data': {'length': 313},
     'text_id': 13,
     'word_positions': [56]},
    '20': {'text_data': {'length': 278},
     'text_id': 20,
     'word_positions': [43]},
    '21': {'text_data': {'length': 282},
     'text_id': 21,
     'word_positions': [41]}},
   'weight': 3}),
 ('cotisation_avs',
  'emp_04',
  {'paths': {'25': {'word_positions': [225]},
    '36': {'word_positions': [406]},
    '37': {'word_positions': [235]}},
   'weight': 3}),
 ('et_libertés',
  '___',
  {'paths': {'11': {'word_positions': [262]},
    '15': {'word_positions': [145]},
    '34': {'word_positions': [252]}},
   'weight': 3}),
 ('être_exercés',
  'auprès',
  {'paths': {'11': {'word_positions': [446]},
    '15': {'word_positions': [328]},
    '34': {'word_positions': [432]}},
   'weight': 3}),
 ('responsable_ssources',
  'humaines',
  {'paths': {'14': {'word_positions': [173]},
    '16': {'word_positions': [182]},
    '4': {'word_positions': [182]}},
   'weight': 3}),
 ('bathvient_bi',
  'station_7',
  {'paths': {'29': {'word_positions': [3]},
    '36': {'word_positions': [185, 4]}},
   'weight': 3}),
 ('en_dehors',
  'de_l',
  {'paths': {'11': {'word_positions': [347]},
    '15': {'word_positions': [230]},
    '34': {'word_positions': [336]}},
   'weight': 3}),
 ('ainsi',
  'transférés_liste',
  {'paths': {'11': {'word_positions': [107]},
    '15': {'word_positions': [111]},
    '34': {'word_positions': [106]}},
   'weight': 3}),
 ('agit',
  'd_une',
  {'paths': {'14': {'word_positions': [113]},
    '16': {'word_positions': [122]},
    '4': {'word_positions': [122]}},
   'weight': 3}),
 ('soient_utilisées',
  'par_le',
  {'paths': {'11': {'word_positions': [423]},
    '15': {'word_positions': [304]},
    '34': {'word_positions': [409]}},
   'weight': 3}),
 ('transférés_liste',
  'des',
  {'paths': {'11': {'word_positions': [109]},
    '15': {'word_positions': [113]},
    '34': {'word_positions': [108]}},
   'weight': 3}),
 ('13011',
  'marseille_34696',
  {'paths': {'0': {'word_positions': [85]},
    '14': {'word_positions': [619]},
    '19': {'word_positions': [101]}},
   'weight': 3}),
 ('41',
  'opers_epf',
  {'paths': {'0': {'word_positions': [172]},
    '14': {'word_positions': [707]},
    '19': {'word_positions': [187]}},
   'weight': 3}),
 ('d_accès',
  'de_rectification',
  {'paths': {'11': {'word_positions': [376]},
    '15': {'word_positions': [258]},
    '34': {'word_positions': [363]}},
   'weight': 3}),
 ('comptes_produits',
  'et_services',
  {'paths': {'11': {'word_positions': [112]},
    '15': {'word_positions': [116]},
    '34': {'word_positions': [111]}},
   'weight': 3}),
 ('ou_la',
  'mise_à',
  {'paths': {'11': {'word_positions': [289]},
    '15': {'word_positions': [172]},
    '34': {'word_positions': [279]}},
   'weight': 3}),
 ('bien_vouloir',
  'effectuer_le',
  {'paths': {'11': {'word_positions': [72]},
    '15': {'word_positions': [74]},
    '34': {'word_positions': [71]}},
   'weight': 3}),
 ('8_65',
  'allocation_enfant',
  {'paths': {'37': {'word_positions': [132]},
    '5': {'word_positions': [132]},
    '7': {'word_positions': [138]}},
   'weight': 3}),
 ('to_be',
  'returned_to',
  {'paths': {'0': {'word_positions': [313]},
    '14': {'word_positions': [849]},
    '19': {'word_positions': [331]}},
   'weight': 3}),
 ('signed_the',
  'french_text',
  {'paths': {'0': {'word_positions': [322]},
    '14': {'word_positions': [858]},
    '19': {'word_positions': [340]}},
   'weight': 3}),
 ('ses_partenaires',
  'contractuels_établis',
  {'paths': {'11': {'word_positions': [341]},
    '15': {'word_positions': [224]},
    '34': {'word_positions': [330]}},
   'weight': 3}),
 ('chf_91',
  '600',
  {'paths': {'0': {'word_positions': [148]},
    '14': {'word_positions': [683]},
    '19': {'word_positions': [165]}},
   'weight': 3}),
 ('en_13',
  'mensualités_gross',
  {'paths': {'0': {'word_positions': [152]},
    '14': {'word_positions': [687]},
    '19': {'word_positions': [169]}},
   'weight': 3}),
 ('les_informations',
  'personnelles_recueillies',
  {'paths': {'11': {'word_positions': [268]},
    '15': {'word_positions': [151]},
    '34': {'word_positions': [258]}},
   'weight': 3}),
 ('le_transfert',
  'de_votre',
  {'paths': {'11': {'word_positions': [281]},
    '15': {'word_positions': [164]},
    '34': {'word_positions': [271]}},
   'weight': 3}),
 ('s_s',
  'maladie_0',
  {'paths': {'13': {'word_positions': [173]},
    '20': {'word_positions': [158]},
    '32': {'word_positions': [175]}},
   'weight': 3}),
 ('s_s',
  'alloc_famil',
  {'paths': {'20': {'word_positions': [198]},
    '21': {'word_positions': [194]},
    '32': {'word_positions': [235]}},
   'weight': 3}),
 ('0_50',
  '3',
  {'paths': {'25': {'word_positions': [245]},
    '37': {'word_positions': [255]},
    '5': {'word_positions': [255]}},
   'weight': 3}),
 ('last_first',
  'name',
  {'paths': {'0': {'word_positions': [74]},
    '14': {'word_positions': [608]},
    '19': {'word_positions': [89]}},
   'weight': 3}),
 ('et_adresse',
  'du_client',
  {'paths': {'11': {'word_positions': [19]},
    '15': {'word_positions': [19]},
    '34': {'word_positions': [18]}},
   'weight': 3}),
 ('selon_art',
  '12_lpers',
  {'paths': {'0': {'word_positions': [228]},
    '14': {'word_positions': [763]},
    '19': {'word_positions': [242]}},
   'weight': 3}),
 ('selon_art',
  '41',
  {'paths': {'0': {'word_positions': [171]},
    '14': {'word_positions': [706]},
    '19': {'word_positions': [186]}},
   'weight': 3}),
 ('nom_prénom',
  'ricaud_benjamin',
  {'paths': {'0': {'word_positions': [64]},
    '14': {'word_positions': [598]},
    '19': {'word_positions': [79]}},
   'weight': 3}),
 ('with_publica',
  'assurance',
  {'paths': {'0': {'word_positions': [206]},
    '14': {'word_positions': [741]},
    '19': {'word_positions': [220]}},
   'weight': 3}),
 ('de_rectification',
  'de',
  {'paths': {'11': {'word_positions': [378]},
    '15': {'word_positions': [260]},
    '34': {'word_positions': [365]}},
   'weight': 3}),
 ('ire_salaire',
  'base_pl',
  {'paths': {'13': {'word_positions': [148]},
    '21': {'word_positions': [136]},
    '32': {'word_positions': [149]}},
   'weight': 3}),
 ('mise_à',
  'disposition_des',
  {'paths': {'11': {'word_positions': [291]},
    '15': {'word_positions': [174]},
    '34': {'word_positions': [281]}},
   'weight': 3}),
 ('75_175',
  '00',
  {'paths': {'37': {'word_positions': [213]},
    '5': {'word_positions': [315, 213]}},
   'weight': 3}),
 ('limites_nécessaires',
  'à_l',
  {'paths': {'11': {'word_positions': [322]},
    '15': {'word_positions': [205]},
    '34': {'word_positions': [312]}},
   'weight': 3}),
 ('mensualités_and',
  'family',
  {'paths': {'0': {'word_positions': [180]},
    '14': {'word_positions': [715]},
    '19': {'word_positions': [194]}},
   'weight': 3}),
 ('à',
  'distance_24',
  {'paths': {'6': {'word_positions': [14]},
    '9': {'word_positions': [233, 13]}},
   'weight': 3}),
 ('à',
  'des_fins',
  {'paths': {'11': {'word_positions': [429]},
    '15': {'word_positions': [311]},
    '34': {'word_positions': [415]}},
   'weight': 3}),
 ('sur',
  'ladite_agence',
  {'paths': {'11': {'word_positions': [94]},
    '15': {'word_positions': [98]},
    '34': {'word_positions': [93]}},
   'weight': 3}),
 ('ap_suva',
  'emp_04',
  {'paths': {'25': {'word_positions': [287]},
    '36': {'word_positions': [94]},
    '37': {'word_positions': [297]}},
   'weight': 3}),
 ('pour',
  'le_transfert',
  {'paths': {'11': {'word_positions': [279]},
    '15': {'word_positions': [162]},
    '34': {'word_positions': [269]}},
   'weight': 3}),
 ('début',
  'du_contrat',
  {'paths': {'0': {'word_positions': [101]},
    '14': {'word_positions': [635]},
    '19': {'word_positions': [117]}},
   'weight': 3}),
 ('bancaire_prospection',
  'animation',
  {'paths': {'11': {'word_positions': [309]},
    '15': {'word_positions': [192]},
    '34': {'word_positions': [299]}},
   'weight': 3}),
 ('votre_conseiller',
  'en_agence',
  {'paths': {'6': {'word_positions': [83]},
    '9': {'word_positions': [271, 45]}},
   'weight': 3}),
 ('et',
  'sans_motif',
  {'paths': {'11': {'word_positions': [412]},
    '15': {'word_positions': [293]},
    '34': {'word_positions': [399]}},
   'weight': 3}),
 ('société_générale',
  'à',
  {'paths': {'11': {'word_positions': [428]},
    '15': {'word_positions': [310]},
    '34': {'word_positions': [414]}},
   'weight': 3}),
 ('société_générale',
  'ayant_recueilli',
  {'paths': {'11': {'word_positions': [454]},
    '15': {'word_positions': [336]},
    '34': {'word_positions': [440]}},
   'weight': 3}),
 ('en_francs',
  'de',
  {'paths': {'6': {'word_positions': [772]},
    '9': {'word_positions': [155, 380]}},
   'weight': 3}),
 ('4_440',
  '00_olympe',
  {'paths': {'37': {'word_positions': [138]},
    '5': {'word_positions': [138]},
    '7': {'word_positions': [144]}},
   'weight': 3}),
 ('à_l',
  'exécution_de',
  {'paths': {'11': {'word_positions': [324]},
    '15': {'word_positions': [207]},
    '34': {'word_positions': [314]}},
   'weight': 3}),
 ('fassent',
  'l_objet',
  {'paths': {'11': {'word_positions': [401]},
    '15': {'word_positions': [282]},
    '34': {'word_positions': [388]}},
   'weight': 3}),
 ('40_40',
  '00_00',
  {'paths': {'29': {'word_positions': [231, 223]},
    '36': {'word_positions': [443]}},
   'weight': 3}),
 ('relation',
  'bancaire_prospection',
  {'paths': {'11': {'word_positions': [307]},
    '15': {'word_positions': [190]},
    '34': {'word_positions': [297]}},
   'weight': 3}),
 ('adresse_12',
  'traverse_de',
  {'paths': {'0': {'word_positions': [79]},
    '14': {'word_positions': [613]},
    '19': {'word_positions': [95]}},
   'weight': 3}),
 ('en_euros',
  'vos',
  {'paths': {'6': {'word_positions': [9]}, '9': {'word_positions': [228, 8]}},
   'weight': 3}),
 ('12',
  'monthly_instalments',
  {'paths': {'0': {'word_positions': [192]},
    '14': {'word_positions': [727]},
    '19': {'word_positions': [206]}},
   'weight': 3}),
 ('12',
  '2016_nom',
  {'paths': {'11': {'word_positions': [15]},
    '15': {'word_positions': [15]},
    '34': {'word_positions': [14]}},
   'weight': 3}),
 ('traitement_des',
  'signaux_2',
  {'paths': {'0': {'word_positions': [96]},
    '14': {'word_positions': [630]},
    '19': {'word_positions': [112]}},
   'weight': 3}),
 ('4_435',
  '00_anthonin',
  {'paths': {'37': {'word_positions': [107]},
    '5': {'word_positions': [107]},
    '7': {'word_positions': [113]}},
   'weight': 3}),
 ('00_olympe',
  '370_00',
  {'paths': {'37': {'word_positions': [140]},
    '5': {'word_positions': [140]},
    '7': {'word_positions': [146]}},
   'weight': 3}),
 ('urssaf_herault',
  'nee_grade',
  {'paths': {'13': {'word_positions': [43]},
    '21': {'word_positions': [28]},
    '32': {'word_positions': [37]}},
   'weight': 3}),
 ('la_case',
  'ci',
  {'paths': {'11': {'word_positions': [438]},
    '15': {'word_positions': [320]},
    '34': {'word_positions': [424]}},
   'weight': 3}),
 ('notice',
  'pursuant_to',
  {'paths': {'0': {'word_positions': [233]},
    '14': {'word_positions': [768]},
    '19': {'word_positions': [247]}},
   'weight': 3}),
 ('téléphone',
  '04_50',
  {'paths': {'6': {'word_positions': [62]},
    '9': {'word_positions': [259, 277]}},
   'weight': 3}),
 ('cotisation_ac',
  'emp',
  {'paths': {'2': {'word_positions': [255]},
    '5': {'word_positions': [259]},
    '7': {'word_positions': [265]}},
   'weight': 3}),
 ('cotisation_ac',
  'emp_04',
  {'paths': {'25': {'word_positions': [249]},
    '36': {'word_positions': [421]},
    '37': {'word_positions': [259]}},
   'weight': 3}),
 ('7',
  '629_85',
  {'paths': {'2': {'word_positions': [224, 339, 333]}}, 'weight': 3}),
 ('7',
  '060_35',
  {'paths': {'25': {'word_positions': [327, 218, 333]}}, 'weight': 3}),
 ('ayant_recueilli',
  'ces_informations',
  {'paths': {'11': {'word_positions': [456]},
    '15': {'word_positions': [338]},
    '34': {'word_positions': [442]}},
   'weight': 3}),
 ('term_of',
  'notice',
  {'paths': {'0': {'word_positions': [232]},
    '14': {'word_positions': [767]},
    '19': {'word_positions': [246]}},
   'weight': 3}),
 ('bl_fax',
  '4121_693',
  {'paths': {'16': {'word_positions': [20]},
    '31': {'word_positions': [16]},
    '4': {'word_positions': [20]}},
   'weight': 3}),
 ('2_864',
  '00_maya',
  {'paths': {'37': {'word_positions': [128]},
    '5': {'word_positions': [128]},
    '7': {'word_positions': [134]}},
   'weight': 3}),
 ('mensualités_gross',
  'annual',
  {'paths': {'0': {'word_positions': [154]},
    '14': {'word_positions': [689]},
    '19': {'word_positions': [171]}},
   'weight': 3}),
 ('pensions',
  'affiliation_à',
  {'paths': {'0': {'word_positions': [197]},
    '14': {'word_positions': [732]},
    '19': {'word_positions': [211]}},
   'weight': 3}),
 ('cotisation_anp',
  'suva_emp',
  {'paths': {'2': {'word_positions': [279]},
    '5': {'word_positions': [283]},
    '7': {'word_positions': [289]}},
   'weight': 3}),
 ('toutes_les',
  'opérations',
  {'paths': {'11': {'word_positions': [98]},
    '15': {'word_positions': [102]},
    '34': {'word_positions': [97]}},
   'weight': 3}),
 ('de_votre',
  'vos',
  {'paths': {'11': {'word_positions': [283]},
    '15': {'word_positions': [166]},
    '34': {'word_positions': [273]}},
   'weight': 3}),
 ('date_précitée',
  'nous_vous',
  {'paths': {'14': {'word_positions': [130]},
    '16': {'word_positions': [139]},
    '4': {'word_positions': [139]}},
   'weight': 3}),
 ('professionnel_accident',
  'insurance_suva',
  {'paths': {'0': {'word_positions': [216]},
    '14': {'word_positions': [751]},
    '19': {'word_positions': [230]}},
   'weight': 3}),
 ('00_00',
  '40_40',
  {'paths': {'29': {'word_positions': [219]},
    '36': {'word_positions': [439, 445]}},
   'weight': 3}),
 ('cotisation',
  'pc_familles',
  {'paths': {'2': {'word_positions': [179]},
    '29': {'word_positions': [85]},
    '36': {'word_positions': [347]}},
   'weight': 3}),
 ('cotisation',
  'anp_suva',
  {'paths': {'29': {'word_positions': [82]},
    '36': {'word_positions': [79, 340]}},
   'weight': 3}),
 ('transfert_de',
  'mes_nos',
  {'paths': {'11': {'word_positions': [76]},
    '15': {'word_positions': [78]},
    '34': {'word_positions': [75]}},
   'weight': 3}),
 ('professionnel_et',
  'non',
  {'paths': {'0': {'word_positions': [213]},
    '14': {'word_positions': [748]},
    '19': {'word_positions': [227]}},
   'weight': 3}),
 ('effectuer_le',
  'transfert_de',
  {'paths': {'11': {'word_positions': [74]},
    '15': {'word_positions': [76]},
    '34': {'word_positions': [73]}},
   'weight': 3}),
 ('s_a',
  'au_capital',
  {'paths': {'11': {'word_positions': [484]},
    '15': {'word_positions': [364]},
    '34': {'word_positions': [467]}},
   'weight': 3}),
 ('employment',
  'percentage',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [129]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [664]},
    '19': {'text_data': {'length': 385},
     'text_id': 19,
     'word_positions': [146]}},
   'weight': 3}),
 ('des',
  'comptes_produits',
  {'paths': {'11': {'word_positions': [110]},
    '15': {'word_positions': [114]},
    '34': {'word_positions': [109]}},
   'weight': 3}),
 ('l_objet',
  'd_un',
  {'paths': {'11': {'word_positions': [403]},
    '15': {'word_positions': [284]},
    '34': {'word_positions': [390]}},
   'weight': 3}),
 ('d_essai',
  '3_mois',
  {'paths': {'0': {'word_positions': [115]},
    '14': {'word_positions': [650]},
    '19': {'word_positions': [131]}},
   'weight': 3}),
 ('d_entretien',
  'selon_art',
  {'paths': {'0': {'word_positions': [169]},
    '14': {'word_positions': [704]},
    '19': {'word_positions': [184]}},
   'weight': 3}),
 ('01_10',
  '2012_fin',
  {'paths': {'0': {'word_positions': [105]},
    '14': {'word_positions': [639]},
    '19': {'word_positions': [121]}},
   'weight': 3}),
 ('et_services',
  'transférés',
  {'paths': {'11': {'word_positions': [114]},
    '15': {'word_positions': [118]},
    '34': {'word_positions': [113]}},
   'weight': 3}),
 ('et_services',
  'souscrits_ce',
  {'paths': {'11': {'word_positions': [296]},
    '15': {'word_positions': [179]},
    '34': {'word_positions': [286]}},
   'weight': 3}),
 ('de_la',
  'société_générale',
  {'paths': {'11': {'word_positions': [452]},
    '15': {'word_positions': [334]},
    '34': {'word_positions': [438]}},
   'weight': 3}),
 ('de_la',
  'relation',
  {'paths': {'11': {'word_positions': [306]},
    '15': {'word_positions': [189]},
    '34': {'word_positions': [296]}},
   'weight': 3}),
 ('de_la',
  'nouvelle_agence',
  {'paths': {'11': {'word_positions': [84]},
    '15': {'word_positions': [86]},
    '34': {'word_positions': [83]}},
   'weight': 3}),
 ('relevé_des',
  'operations',
  {'paths': {'6': {'word_positions': [107]},
    '9': {'word_positions': [60, 285]}},
   'weight': 3}),
 ('lausanne_le',
  '23_juin',
  {'paths': {'14': {'word_positions': [74]},
    '16': {'word_positions': [81]},
    '4': {'word_positions': [81]}},
   'weight': 3}),
 ('sip',
  'thonon',
  {'paths': {'8': {'text_data': {'length': 779},
     'text_id': 8,
     'word_positions': [49, 709, 728]}},
   'weight': 3}),
 ('de_résiliation',
  'selon_art',
  {'paths': {'0': {'word_positions': [226]},
    '14': {'word_positions': [761]},
    '19': {'word_positions': [240]}},
   'weight': 3}),
 ('05_2015',
  'fct',
  {'paths': {'2': {'word_positions': [66]},
    '36': {'word_positions': [54, 214]}},
   'weight': 3}),
 ('july_25',
  '2012',
  {'paths': {'0': {'word_positions': [44]},
    '14': {'word_positions': [578]},
    '19': {'word_positions': [50]}},
   'weight': 3}),
 ('pour_vous',
  'aider_a',
  {'paths': {'13': {'word_positions': [296]},
    '21': {'word_positions': [266]},
    '32': {'word_positions': [311]}},
   'weight': 3}),
 ('en_agence',
  'mme',
  {'paths': {'6': {'word_positions': [85]},
    '9': {'word_positions': [273, 47]}},
   'weight': 3}),
 ('date_14',
  '12',
  {'paths': {'11': {'word_positions': [14]},
    '15': {'word_positions': [14]},
    '34': {'word_positions': [13]}},
   'weight': 3}),
 ('73_675',
  '00',
  {'paths': {'36': {'word_positions': [112]},
    '7': {'word_positions': [321, 219]}},
   'weight': 3}),
 ('il_s',
  'agit',
  {'paths': {'14': {'word_positions': [112]},
    '16': {'word_positions': [121]},
    '4': {'word_positions': [121]}},
   'weight': 3}),
 ('disposez',
  'd_un',
  {'paths': {'11': {'word_positions': [371]},
    '15': {'word_positions': [253]},
    '34': {'word_positions': [358]}},
   'weight': 3}),
 ('légales_legal',
  'requirements',
  {'paths': {'0': {'word_positions': [347]},
    '14': {'word_positions': [883]},
    '19': {'word_positions': [364]}},
   'weight': 3}),
 ('de_lausanne',
  'monsieur',
  {'paths': {'14': {'word_positions': [433, 60, 256]}}, 'weight': 3}),
 ('de_lausanne',
  'epfl_et',
  {'paths': {'0': {'word_positions': [59]},
    '14': {'word_positions': [593]},
    '19': {'word_positions': [67]}},
   'weight': 3}),
 ('maladie_0',
  'base_depla',
  {'paths': {'13': {'word_positions': [175]},
    '20': {'word_positions': [160]},
    '32': {'word_positions': [177]}},
   'weight': 3}),
 ('personne_s',
  'à_charge',
  {'paths': {'8': {'word_positions': [456, 465, 350]}}, 'weight': 3}),
 ('titulaire',
  'nouveau',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [121]},
    '15': {'text_data': {'length': 388},
     'text_id': 15,
     'word_positions': [125]},
    '34': {'text_data': {'length': 490},
     'text_id': 34,
     'word_positions': [120]}},
   'weight': 3}),
 ('anp_suva',
  'emp_04',
  {'paths': {'25': {'word_positions': [274]},
    '36': {'word_positions': [81]},
    '37': {'word_positions': [284]}},
   'weight': 3}),
 ('function_rattachement',
  'laboratoire_de',
  {'paths': {'0': {'word_positions': [92]},
    '14': {'word_positions': [626]},
    '19': {'word_positions': [108]}},
   'weight': 3}),
 ('de_compte',
  'compte_de',
  {'paths': {'6': {'word_positions': [288, 4, 517]}}, 'weight': 3}),
 ('non',
  'professionnel_accident',
  {'paths': {'0': {'word_positions': [214]},
    '14': {'word_positions': [749]},
    '19': {'word_positions': [228]}},
   'weight': 3}),
 ('effe',
  'de_personnel',
  {'paths': {'1': {'word_positions': [156]},
    '14': {'word_positions': [526]},
    '31': {'word_positions': [161]}},
   'weight': 3}),
 ('nous_précisons',
  'qu',
  {'paths': {'14': {'word_positions': [109]},
    '16': {'word_positions': [118]},
    '4': {'word_positions': [118]}},
   'weight': 3}),
 ('1_des',
  'co',
  {'paths': {'11': {'word_positions': [475]},
    '15': {'word_positions': [354]},
    '34': {'word_positions': [458]}},
   'weight': 3}),
 ('cot',
  'périodique_cp',
  {'paths': {'25': {'word_positions': [298]},
    '36': {'word_positions': [105]},
    '37': {'word_positions': [308]}},
   'weight': 3}),
 ('doyen_gaston',
  'giraud',
  {'paths': {'13': {'word_positions': [32]},
    '21': {'word_positions': [19]},
    '32': {'word_positions': [27]}},
   'weight': 3}),
 ('accident_suva',
  'pour_accidents',
  {'paths': {'0': {'word_positions': [209]},
    '14': {'word_positions': [744]},
    '19': {'word_positions': [223]}},
   'weight': 3}),
 ('site_web',
  'http',
  {'paths': {'0': {'word_positions': [37]},
    '16': {'word_positions': [44]},
    '4': {'word_positions': [44]}},
   'weight': 3}),
 ('12_lpers',
  'dispositions',
  {'paths': {'0': {'word_positions': [238]},
    '14': {'word_positions': [773]},
    '19': {'word_positions': [252]}},
   'weight': 3}),
 ('12_lpers',
  'term_of',
  {'paths': {'0': {'word_positions': [230]},
    '14': {'word_positions': [765]},
    '19': {'word_positions': [244]}},
   'weight': 3}),
 ('d_activité',
  'employment',
  {'paths': {'0': {'word_positions': [128]},
    '14': {'word_positions': [663]},
    '19': {'word_positions': [145]}},
   'weight': 3}),
 ('maladie',
  'depl_maladie',
  {'paths': {'13': {'word_positions': [89]},
    '21': {'word_positions': [77]},
    '32': {'word_positions': [84]}},
   'weight': 3}),
 ('lahille',
  '253_rue',
  {'paths': {'11': {'word_positions': [24]},
    '15': {'word_positions': [26]},
    '34': {'word_positions': [23]}},
   'weight': 3}),
 ('des_fins',
  'de',
  {'paths': {'11': {'word_positions': [431]},
    '15': {'word_positions': [313]},
    '34': {'word_positions': [417]}},
   'weight': 3}),
 ('co',
  'titulaires_si',
  {'paths': {'11': {'word_positions': [476]},
    '15': {'word_positions': [355]},
    '34': {'word_positions': [459]}},
   'weight': 3}),
 ('epfl_wannier',
  'responsable_ssources',
  {'paths': {'14': {'word_positions': [171]},
    '16': {'word_positions': [180]},
    '4': {'word_positions': [180]}},
   'weight': 3}),
 ('marseille_34696',
  'fonction',
  {'paths': {'0': {'word_positions': [87]},
    '14': {'word_positions': [621]},
    '19': {'word_positions': [103]}},
   'weight': 3}),
 ('references_dispositions',
  'légales_legal',
  {'paths': {'0': {'word_positions': [345]},
    '14': {'word_positions': [881]},
    '19': {'word_positions': [362]}},
   'weight': 3}),
 ('in',
  '13',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [157]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [692]},
    '19': {'text_data': {'length': 385},
     'text_id': 19,
     'word_positions': [174]}},
   'weight': 3}),
 ('in',
  'accordance_with',
  {'paths': {'0': {'word_positions': [336]},
    '14': {'word_positions': [872]},
    '19': {'word_positions': [353]}},
   'weight': 3}),
 ('accidents_délai',
  'de_résiliation',
  {'paths': {'0': {'word_positions': [224]},
    '14': {'word_positions': [759]},
    '19': {'word_positions': [238]}},
   'weight': 3}),
 ('de_l',
  'union',
  {'paths': {'11': {'word_positions': [349]},
    '15': {'word_positions': [232]},
    '34': {'word_positions': [338]}},
   'weight': 3}),
 ('risque_cp',
  'emp_04',
  {'paths': {'25': {'word_positions': [313]},
    '36': {'word_positions': [120]},
    '37': {'word_positions': [323]}},
   'weight': 3}),
 ('nature',
  'de_l',
  {'paths': {'6': {'word_positions': [296, 658]},
    '9': {'word_positions': [91]}},
   'weight': 3}),
 ('caisse_de',
  'pensions',
  {'paths': {'0': {'word_positions': [196]},
    '14': {'word_positions': [731]},
    '19': {'word_positions': [210]}},
   'weight': 3}),
 ('3933_votre',
  'agence_thonon',
  {'paths': {'6': {'word_positions': [49]},
    '9': {'word_positions': [25, 247]}},
   'weight': 3}),
 ('dispositions',
  'particulières',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [239]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [774]},
    '19': {'text_data': {'length': 385},
     'text_id': 19,
     'word_positions': [253]}},
   'weight': 3}),
 ('transfert',
  'de_compte',
  {'paths': {'11': {'word_positions': [4]},
    '15': {'word_positions': [4]},
    '34': {'word_positions': [4]}},
   'weight': 3}),
 ('du_titre',
  'de',
  {'paths': {'0': {'word_positions': [254]},
    '14': {'word_positions': [789]},
    '19': {'word_positions': [269]}},
   'weight': 3}),
 ('à_assurer',
  'la_protection',
  {'paths': {'11': {'word_positions': [363]},
    '15': {'word_positions': [245]},
    '34': {'word_positions': [350]}},
   'weight': 3}),
 ('solde',
  'en_francs',
  {'paths': {'6': {'word_positions': [770]},
    '9': {'word_positions': [153, 378]}},
   'weight': 3}),
 ('vieillesse_pat',
  'deplaf',
  {'paths': {'20': {'word_positions': [205]},
    '21': {'word_positions': [201]},
    '32': {'word_positions': [244]}},
   'weight': 3}),
 ('bâtiment_bi',
  'fax',
  {'paths': {'1': {'word_positions': [15]},
    '14': {'word_positions': [209, 11]}},
   'weight': 3}),
 ('demande_de',
  'transfert',
  {'paths': {'11': {'word_positions': [3]},
    '15': {'word_positions': [3]},
    '34': {'word_positions': [3]}},
   'weight': 3}),
 ('monthly_instalments',
  'caisse_de',
  {'paths': {'0': {'word_positions': [194]},
    '14': {'word_positions': [729]},
    '19': {'word_positions': [208]}},
   'weight': 3}),
 ('nouvelle_agence',
  '00111_evian',
  {'paths': {'11': {'word_positions': [43]},
    '15': {'word_positions': [45]},
    '34': {'word_positions': [42]}},
   'weight': 3}),
 ('nouvelle_agence',
  'ci',
  {'paths': {'11': {'word_positions': [86]},
    '15': {'word_positions': [88]},
    '34': {'word_positions': [85]}},
   'weight': 3}),
 ('30_septembre',
  '2016',
  {'paths': {'14': {'word_positions': [106]},
    '16': {'word_positions': [115]},
    '4': {'word_positions': [115]}},
   'weight': 3}),
 ('jour',
  'pour_des',
  {'paths': {'11': {'word_positions': [299]},
    '15': {'word_positions': [182]},
    '34': {'word_positions': [289]}},
   'weight': 3}),
 ('pour_accidents',
  'professionnel_et',
  {'paths': {'0': {'word_positions': [211]},
    '14': {'word_positions': [746]},
    '19': {'word_positions': [225]}},
   'weight': 3}),
 ('a1_407',
  'bâtiment',
  {'paths': {'16': {'word_positions': [17]},
    '31': {'word_positions': [13]},
    '4': {'word_positions': [17]}},
   'weight': 3}),
 ('allocation_enfant',
  '04_16',
  {'paths': {'37': {'word_positions': [134, 113, 92]}}, 'weight': 3}),
 ('allocation_enfant',
  '04_15',
  {'paths': {'36': {'word_positions': [299, 273, 286]}}, 'weight': 3}),
 ('allocation_enfant',
  '12_15',
  {'paths': {'7': {'word_positions': [140, 98, 119]}}, 'weight': 3}),
 ('allocation_enfant',
  '12_14',
  {'paths': {'2': {'word_positions': [98, 119]},
    '36': {'word_positions': [249]}},
   'weight': 3}),
 ('allocation_enfant',
  '08_16',
  {'paths': {'5': {'word_positions': [134, 92, 113]}}, 'weight': 3}),
 ('370_00',
  'brut',
  {'paths': {'37': {'word_positions': [142]},
    '5': {'word_positions': [142]},
    '7': {'word_positions': [148]}},
   'weight': 3}),
 ('00_5',
  '85',
  {'paths': {'37': {'word_positions': [203]},
    '5': {'word_positions': [203]},
    '7': {'word_positions': [209]}},
   'weight': 3}),
 ('qui_prendra',
  'définitivement_fin',
  {'paths': {'14': {'word_positions': [124]},
    '16': {'word_positions': [133]},
    '4': {'word_positions': [133]}},
   'weight': 3}),
 ('collaborateur_scientifique',
  'function_rattachement',
  {'paths': {'0': {'word_positions': [90]},
    '14': {'word_positions': [624]},
    '19': {'word_positions': [106]}},
   'weight': 3}),
 ('d_une',
  'ultime_prolongation',
  {'paths': {'14': {'word_positions': [115]},
    '16': {'word_positions': [124]},
    '4': {'word_positions': [124]}},
   'weight': 3}),
 ('remboursem',
  'dette_sociale',
  {'paths': {'13': {'word_positions': [186]},
    '21': {'word_positions': [165]},
    '32': {'word_positions': [188]}},
   'weight': 3}),
 ('307_30',
  '00_00',
  {'paths': {'20': {'word_positions': [128]},
    '21': {'word_positions': [121]},
    '32': {'word_positions': [128]}},
   'weight': 3}),
 ('dec_annemasse',
  'nouvelle_agence',
  {'paths': {'11': {'word_positions': [41]},
    '15': {'word_positions': [43]},
    '34': {'word_positions': [40]}},
   'weight': 3}),
 ('___',
  'les_informations',
  {'paths': {'11': {'word_positions': [266]},
    '15': {'word_positions': [149]},
    '34': {'word_positions': [256]}},
   'weight': 3}),
 ('hr_department',
  'duly',
  {'paths': {'0': {'word_positions': [317]},
    '14': {'word_positions': [853]},
    '19': {'word_positions': [335]}},
   'weight': 3}),
 ('vandergheynst',
  'l_employé',
  {'paths': {'14': {'word_positions': [535, 360, 181]}}, 'weight': 3}),
 ('souscrits_ce',
  'jour',
  {'paths': {'11': {'word_positions': [298]},
    '15': {'word_positions': [181]},
    '34': {'word_positions': [288]}},
   'weight': 3}),
 ('limitation',
  'de_duree',
  {'paths': {'13': {'word_positions': [310]},
    '20': {'word_positions': [275]},
    '21': {'word_positions': [279]}},
   'weight': 3}),
 ('00111_001',
  'date_14',
  {'paths': {'11': {'word_positions': [12]},
    '15': {'word_positions': [12]},
    '34': {'word_positions': [11]}},
   'weight': 3}),
 ('bancaire_sg',
  'montpellier_facultes',
  {'paths': {'13': {'word_positions': [53]},
    '20': {'word_positions': [33]},
    '21': {'word_positions': [38]}},
   'weight': 3}),
 ('dans_les',
  'limites_nécessaires',
  {'paths': {'11': {'word_positions': [320]},
    '15': {'word_positions': [203]},
    '34': {'word_positions': [310]}},
   'weight': 3}),
 ('percentage',
  '100_41',
  {'paths': {'0': {'word_positions': [130]},
    '14': {'word_positions': [665]},
    '19': {'word_positions': [147]}},
   'weight': 3}),
 ('2016',
  'nous_précisons',
  {'paths': {'14': {'word_positions': [107]},
    '16': {'word_positions': [116]},
    '4': {'word_positions': [116]}},
   'weight': 3}),
 ('04_50',
  '75_12',
  {'paths': {'11': {'word_positions': [50]},
    '15': {'word_positions': [52]},
    '34': {'word_positions': [49]}},
   'weight': 3}),
 ('2012_fin',
  'du_contrat',
  {'paths': {'0': {'word_positions': [107]},
    '14': {'word_positions': [641]},
    '19': {'word_positions': [123]}},
   'weight': 3}),
 ('00_1',
  '25',
  {'paths': {'36': {'word_positions': [127]},
    '5': {'word_positions': [330]},
    '7': {'word_positions': [336]}},
   'weight': 3}),
 ('assurance',
  'accident_suva',
  {'paths': {'0': {'word_positions': [207]},
    '14': {'word_positions': [742]},
    '19': {'word_positions': [221]}},
   'weight': 3}),
 ('faire_valoir',
  'vos_droits',
  {'paths': {'13': {'word_positions': [300]},
    '21': {'word_positions': [270]},
    '32': {'word_positions': [315]}},
   'weight': 3}),
 ('certificat',
  'd_assurance',
  {'paths': {'22': {'word_positions': [33, 50]},
    '26': {'word_positions': [50]}},
   'weight': 3}),
 ('affiliation_à',
  'publica',
  {'paths': {'0': {'word_positions': [199]},
    '14': {'word_positions': [734]},
    '19': {'word_positions': [213]}},
   'weight': 3}),
 ('laboratoire_de',
  'traitement_des',
  {'paths': {'0': {'word_positions': [94]},
    '14': {'word_positions': [628]},
    '19': {'word_positions': [110]}},
   'weight': 3}),
 ('payable_in',
  '12',
  {'paths': {'0': {'word_positions': [191]},
    '14': {'word_positions': [726]},
    '19': {'word_positions': [205]}},
   'weight': 3}),
 ('en_12',
  'mensualités_and',
  {'paths': {'0': {'word_positions': [178]},
    '14': {'word_positions': [713]},
    '19': {'word_positions': [192]}},
   'weight': 3}),
 ('taux',
  'd_activité',
  {'paths': {'0': {'word_positions': [126]},
    '14': {'word_positions': [661]},
    '19': {'word_positions': [143]}},
   'weight': 3}),
 ('ressources_humaines',
  'dûment',
  {'paths': {'0': {'word_positions': [300]},
    '14': {'word_positions': [835]},
    '19': {'word_positions': [322]}},
   'weight': 3}),
 ('00111_evian',
  'les_bains',
  {'paths': {'11': {'word_positions': [45]},
    '15': {'word_positions': [47]},
    '34': {'word_positions': [44]}},
   'weight': 3}),
 ('particulières',
  'special_clauses',
  {'paths': {'0': {'word_positions': [240]},
    '14': {'word_positions': [775]},
    '19': {'word_positions': [254]}},
   'weight': 3}),
 ('naissance',
  '13_07',
  {'paths': {'0': {'word_positions': [69]},
    '14': {'word_positions': [603]},
    '19': {'word_positions': [84]}},
   'weight': 3}),
 ('d_un',
  'droit',
  {'paths': {'11': {'word_positions': [373]},
    '15': {'word_positions': [255]},
    '34': {'word_positions': [360]}},
   'weight': 3}),
 ('et_études',
  'statistiques_et',
  {'paths': {'11': {'word_positions': [313]},
    '15': {'word_positions': [196]},
    '34': {'word_positions': [303]}},
   'weight': 3}),
 ('de_travail',
  'contract_of',
  {'paths': {'0': {'word_positions': [48]},
    '14': {'word_positions': [582]},
    '19': {'word_positions': [54]}},
   'weight': 3}),
 ('de_travail',
  'qui_prendra',
  {'paths': {'14': {'word_positions': [122]},
    '16': {'word_positions': [131]},
    '4': {'word_positions': [131]}},
   'weight': 3}),
 ('00_maya',
  '8_65',
  {'paths': {'37': {'word_positions': [130]},
    '5': {'word_positions': [130]},
    '7': {'word_positions': [136]}},
   'weight': 3}),
 ('ultime_prolongation',
  'de_votre',
  {'paths': {'14': {'word_positions': [117]},
    '16': {'word_positions': [126]},
    '4': {'word_positions': [126]}},
   'weight': 3}),
 ('contre__',
  'ces_droits',
  {'paths': {'11': {'word_positions': [441]},
    '15': {'word_positions': [323]},
    '34': {'word_positions': [427]}},
   'weight': 3}),
 ('11_11',
  'bl',
  {'paths': {'14': {'word_positions': [204, 382]}}, 'weight': 2}),
 ('fédérale_de',
  'compensation',
  {'paths': {'22': {'word_positions': [190]}, '26': {'word_positions': [190]}},
   'weight': 2}),
 ('takes',
  'precedence',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [325]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [861]}},
   'weight': 2}),
 ('338',
  'cumul_du',
  {'paths': {'13': {'word_positions': [256]}, '32': {'word_positions': [256]}},
   'weight': 2}),
 ('this',
  'contract_of',
  {'paths': {'0': {'word_positions': [327]}, '14': {'word_positions': [863]}},
   'weight': 2}),
 ('nouveau',
  'numéro',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [122]},
    '15': {'text_data': {'length': 388},
     'text_id': 15,
     'word_positions': [126]}},
   'weight': 2}),
 ('c',
  'est',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [55]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [55]}},
   'weight': 2}),
 ('de_salaire',
  'décembre',
  {'paths': {'2': {'word_positions': [36]}, '7': {'word_positions': [36]}},
   'weight': 2}),
 ('389_83',
  '39',
  {'paths': {'29': {'word_positions': [273]}, '36': {'word_positions': [486]}},
   'weight': 2}),
 ('m',
  'ricaud_benjamin',
  {'paths': {'8': {'word_positions': [300, 69]}}, 'weight': 2}),
 ('m',
  'epfl_ch',
  {'paths': {'14': {'word_positions': [49, 564]}}, 'weight': 2}),
 ('m',
  'm_l',
  {'paths': {'13': {'word_positions': [106]}, '21': {'word_positions': [92]}},
   'weight': 2}),
 ('m',
  'epfl_ch',
  {'paths': {'14': {'word_positions': [398]}, '19': {'word_positions': [30]}},
   'weight': 2}),
 ('00',
  '100_00',
  {'paths': {'37': {'word_positions': [85]}, '7': {'word_positions': [85]}},
   'weight': 2}),
 ('00',
  'fax',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [67]},
    '9': {'text_data': {'length': 451},
     'text_id': 9,
     'word_positions': [264]}},
   'weight': 2}),
 ('00',
  '625',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [935]},
    '9': {'text_data': {'length': 451},
     'text_id': 9,
     'word_positions': [438]}},
   'weight': 2}),
 ('00',
  '2',
  {'paths': {'8': {'text_data': {'length': 779},
     'text_id': 8,
     'word_positions': [306]},
    '9': {'text_data': {'length': 451},
     'text_id': 9,
     'word_positions': [135]}},
   'weight': 2}),
 ('00',
  '607',
  {'paths': {'29': {'text_data': {'length': 336},
     'text_id': 29,
     'word_positions': [288]},
    '36': {'text_data': {'length': 567},
     'text_id': 36,
     'word_positions': [502]}},
   'weight': 2}),
 ('00',
  '65',
  {'paths': {'29': {'text_data': {'length': 336},
     'text_id': 29,
     'word_positions': [286]},
    '36': {'text_data': {'length': 567},
     'text_id': 36,
     'word_positions': [500]}},
   'weight': 2}),
 ('00',
  '1_10',
  {'paths': {'2': {'word_positions': [210]}, '25': {'word_positions': [204]}},
   'weight': 2}),
 ('00',
  '10_40',
  {'paths': {'36': {'word_positions': [113]}, '7': {'word_positions': [322]}},
   'weight': 2}),
 ('0600',
  '5',
  {'paths': {'29': {'text_data': {'length': 336},
     'text_id': 29,
     'word_positions': [244]},
    '36': {'text_data': {'length': 567},
     'text_id': 36,
     'word_positions': [465]}},
   'weight': 2}),
 ('pourront',
  'dans_les',
  {'paths': {'11': {'word_positions': [318]}, '15': {'word_positions': [201]}},
   'weight': 2}),
 ('diffère',
  'par',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [141]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [141]}},
   'weight': 2}),
 ('507_cotisation',
  'anp_suva',
  {'paths': {'37': {'word_positions': [171]}, '5': {'word_positions': [171]}},
   'weight': 2}),
 ('85',
  '1_10',
  {'paths': {'2': {'word_positions': [261]}, '7': {'word_positions': [271]}},
   'weight': 2}),
 ('85',
  '1_1000',
  {'paths': {'2': {'word_positions': [162]}, '7': {'word_positions': [172]}},
   'weight': 2}),
 ('85',
  '366',
  {'paths': {'37': {'text_data': {'length': 349},
     'text_id': 37,
     'word_positions': [204]},
    '5': {'text_data': {'length': 349},
     'text_id': 5,
     'word_positions': [204]}},
   'weight': 2}),
 ('à_retourner',
  'aux',
  {'paths': {'0': {'word_positions': [297]}, '14': {'word_positions': [832]}},
   'weight': 2}),
 ('epe',
  '04_16',
  {'paths': {'37': {'word_positions': [103, 124]}}, 'weight': 2}),
 ('epe',
  '04_14',
  {'paths': {'25': {'word_positions': [103, 124]}}, 'weight': 2}),
 ('epe',
  'allocation_enfant',
  {'paths': {'29': {'word_positions': [74, 69]}}, 'weight': 2}),
 ('659',
  '05',
  {'paths': {'37': {'text_data': {'length': 349},
     'text_id': 37,
     'word_positions': [147]},
    '5': {'text_data': {'length': 349},
     'text_id': 5,
     'word_positions': [147]}},
   'weight': 2}),
 ('domaine',
  'des',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [371]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [907]}},
   'weight': 2}),
 ('erreurs',
  'ou_la',
  {'paths': {'22': {'word_positions': [160]}, '26': {'word_positions': [160]}},
   'weight': 2}),
 ('01',
  '1',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [490]},
    '9': {'text_data': {'length': 451},
     'text_id': 9,
     'word_positions': [138]}},
   'weight': 2}),
 ('01',
  '307_30',
  {'paths': {'21': {'word_positions': [119]}, '32': {'word_positions': [126]}},
   'weight': 2}),
 ('01',
  '09',
  {'paths': {'37': {'text_data': {'length': 349},
     'text_id': 37,
     'word_positions': [64]},
    '5': {'text_data': {'length': 349}, 'text_id': 5, 'word_positions': [64]}},
   'weight': 2}),
 ('01',
  '7',
  {'paths': {'14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [190]},
    '6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [497]}},
   'weight': 2}),
 ('20',
  'contractuel',
  {'paths': {'13': {'text_data': {'length': 313},
     'text_id': 13,
     'word_positions': [76]},
    '32': {'text_data': {'length': 328},
     'text_id': 32,
     'word_positions': [72]}},
   'weight': 2}),
 ('insurance_suva',
  'professional',
  {'paths': {'0': {'word_positions': [218]}, '14': {'word_positions': [753]}},
   'weight': 2}),
 ('16_75',
  '175_00',
  {'paths': {'37': {'word_positions': [327, 314]}}, 'weight': 2}),
 ('00352',
  '00030474981',
  {'paths': {'9': {'text_data': {'length': 451},
     'text_id': 9,
     'word_positions': [64, 291]}},
   'weight': 2}),
 ('0_75',
  '47',
  {'paths': {'37': {'word_positions': [216]}, '5': {'word_positions': [216]}},
   'weight': 2}),
 ('regist',
  're',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [118]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [118]}},
   'weight': 2}),
 ('de_vos',
  'données',
  {'paths': {'11': {'word_positions': [367]}, '15': {'word_positions': [249]}},
   'weight': 2}),
 ('1000',
  '5267',
  {'paths': {'29': {'text_data': {'length': 336},
     'text_id': 29,
     'word_positions': [242]},
    '36': {'text_data': {'length': 567},
     'text_id': 36,
     'word_positions': [463]}},
   'weight': 2}),
 ('s',
  'pursuant_to',
  {'paths': {'0': {'word_positions': [183]}, '14': {'word_positions': [718]}},
   'weight': 2}),
 ('s',
  'd_entretien',
  {'paths': {'0': {'word_positions': [167]}, '14': {'word_positions': [702]}},
   'weight': 2}),
 ('s',
  'en_12',
  {'paths': {'0': {'word_positions': [176]}, '14': {'word_positions': [711]}},
   'weight': 2}),
 ('plan',
  'd',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [149]},
    '34': {'text_data': {'length': 490},
     'text_id': 34,
     'word_positions': [146]}},
   'weight': 2}),
 ('pursuant_to',
  'art_41',
  {'paths': {'0': {'word_positions': [185]}, '14': {'word_positions': [720]}},
   'weight': 2}),
 ('pursuant_to',
  'art',
  {'paths': {'0': {'word_positions': [235]}, '14': {'word_positions': [770]}},
   'weight': 2}),
 ('exceptionnellement',
  'tire',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [123]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [123]}},
   'weight': 2}),
 ('100',
  'ircantec',
  {'paths': {'13': {'text_data': {'length': 313},
     'text_id': 13,
     'word_positions': [250]},
    '32': {'text_data': {'length': 328},
     'text_id': 32,
     'word_positions': [251]}},
   'weight': 2}),
 ('16',
  'che',
  {'paths': {'8': {'text_data': {'length': 779},
     'text_id': 8,
     'word_positions': [82, 121]}},
   'weight': 2}),
 ('16',
  'fr',
  {'paths': {'14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [263]},
    '31': {'text_data': {'length': 181},
     'text_id': 31,
     'word_positions': [74]}},
   'weight': 2}),
 ('2014',
  'nous_vous',
  {'paths': {'14': {'word_positions': [305]}, '31': {'word_positions': [116]}},
   'weight': 2}),
 ('2014',
  'personnel_monsieur',
  {'paths': {'2': {'word_positions': [38]}, '25': {'word_positions': [38]}},
   'weight': 2}),
 ('valeur',
  'indicative',
  {'paths': {'9': {'text_data': {'length': 451},
     'text_id': 9,
     'word_positions': [82, 322]}},
   'weight': 2}),
 ('valeur',
  'locative',
  {'paths': {'8': {'text_data': {'length': 779},
     'text_id': 8,
     'word_positions': [331, 337]}},
   'weight': 2}),
 ('2015',
  'envoi_n',
  {'paths': {'6': {'word_positions': [532]}, '9': {'word_positions': [299]}},
   'weight': 2}),
 ('2015',
  'sur_proposition',
  {'paths': {'16': {'word_positions': [84]}, '4': {'word_positions': [84]}},
   'weight': 2}),
 ('2015',
  'matricule_34696',
  {'paths': {'29': {'word_positions': [42]}, '36': {'word_positions': [198]}},
   'weight': 2}),
 ('2015',
  'personnel_monsieur',
  {'paths': {'36': {'word_positions': [26]}, '7': {'word_positions': [38]}},
   'weight': 2}),
 ('2015',
  'nous_vous',
  {'paths': {'1': {'word_positions': [112]}, '14': {'word_positions': [482]}},
   'weight': 2}),
 ('données',
  'officielles',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [106]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [106]}},
   'weight': 2}),
 ('données',
  'fassent',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [400]},
    '15': {'text_data': {'length': 388},
     'text_id': 15,
     'word_positions': [281]}},
   'weight': 2}),
 ('données',
  'interviennent',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [355]},
    '15': {'text_data': {'length': 388},
     'text_id': 15,
     'word_positions': [238]}},
   'weight': 2}),
 ('données',
  'soient_utilisées',
  {'paths': {'11': {'word_positions': [421]}, '15': {'word_positions': [302]}},
   'weight': 2}),
 ('65',
  '00',
  {'paths': {'29': {'text_data': {'length': 336},
     'text_id': 29,
     'word_positions': [287]},
    '36': {'text_data': {'length': 567},
     'text_id': 36,
     'word_positions': [501]}},
   'weight': 2}),
 ('65',
  '922',
  {'paths': {'29': {'text_data': {'length': 336},
     'text_id': 29,
     'word_positions': [305]},
    '36': {'text_data': {'length': 567},
     'text_id': 36,
     'word_positions': [525]}},
   'weight': 2}),
 ('rebecca',
  'lahille',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [23]},
    '28': {'text_data': {'length': 103},
     'text_id': 28,
     'word_positions': [32]}},
   'weight': 2}),
 ('rebecca',
  'marie',
  {'paths': {'8': {'text_data': {'length': 779},
     'text_id': 8,
     'word_positions': [75, 311]}},
   'weight': 2}),
 ('907_cotisation',
  'pc_familles',
  {'paths': {'37': {'word_positions': [183]}, '5': {'word_positions': [183]}},
   'weight': 2}),
 ('87',
  '407_cotisation',
  {'paths': {'2': {'word_positions': [264, 165]}}, 'weight': 2}),
 ('termination',
  'date_probation',
  {'paths': {'0': {'word_positions': [120]}, '14': {'word_positions': [655]}},
   'weight': 2}),
 ('taux_d',
  'imposition',
  {'paths': {'8': {'word_positions': [398, 414]}}, 'weight': 2}),
 ('o',
  'epfl_wannier',
  {'paths': {'16': {'word_positions': [178]}, '4': {'word_positions': [178]}},
   'weight': 2}),
 ('0_2633',
  '19',
  {'paths': {'25': {'word_positions': [282]}, '36': {'word_positions': [89]}},
   'weight': 2}),
 ('assuré',
  'susmentionné',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [61]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [61]}},
   'weight': 2}),
 ('h',
  'lsem',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [133]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [668]}},
   'weight': 2}),
 ('64',
  '907',
  {'paths': {'2': {'text_data': {'length': 345},
     'text_id': 2,
     'word_positions': [213]},
    '25': {'text_data': {'length': 339},
     'text_id': 25,
     'word_positions': [207]}},
   'weight': 2}),
 ('retraite',
  'en',
  {'paths': {'13': {'text_data': {'length': 313},
     'text_id': 13,
     'word_positions': [279]},
    '21': {'text_data': {'length': 282},
     'text_id': 21,
     'word_positions': [252]}},
   'weight': 2}),
 ('presta',
  'i',
  {'paths': {'34': {'text_data': {'length': 490},
     'text_id': 34,
     'word_positions': [167, 221]}},
   'weight': 2}),
 ('devant',
  'figurer',
  {'paths': {'28': {'text_data': {'length': 103},
     'text_id': 28,
     'word_positions': [59, 81]}},
   'weight': 2}),
 ('toutes',
  'erreurs',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [159]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [159]}},
   'weight': 2}),
 ('raymonds',
  'address_fr',
  {'paths': {'0': {'word_positions': [82]}, '14': {'word_positions': [616]}},
   'weight': 2}),
 ('prestations',
  'par',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [96]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [96]}},
   'weight': 2}),
 ('ou',
  'service',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [119]},
    '15': {'text_data': {'length': 388},
     'text_id': 15,
     'word_positions': [123]}},
   'weight': 2}),
 ('ou',
  'exceptionnellement',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [122]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [122]}},
   'weight': 2}),
 ('ou',
  'l',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [81]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [81]}},
   'weight': 2}),
 ('ou',
  'lors',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [90]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [90]}},
   'weight': 2}),
 ('eur',
  'siège',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [616]},
    '9': {'text_data': {'length': 451},
     'text_id': 9,
     'word_positions': [441]}},
   'weight': 2}),
 ('renseignement',
  'complémentaire',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [175]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [175]}},
   'weight': 2}),
 ('est',
  'sous',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [56]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [56]}},
   'weight': 2}),
 ('est',
  'de',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [830, 835]}},
   'weight': 2}),
 ('est',
  'à_retourner',
  {'paths': {'0': {'word_positions': [295]}, '14': {'word_positions': [830]}},
   'weight': 2}),
 ('period_3',
  'months',
  {'paths': {'0': {'word_positions': [124]}, '14': {'word_positions': [659]}},
   'weight': 2}),
 ('5_1500',
  '422',
  {'paths': {'7': {'word_positions': [249, 163]}}, 'weight': 2}),
 ('n_30003',
  '00352',
  {'paths': {'9': {'word_positions': [290, 63]}}, 'weight': 2}),
 ('effective',
  'date',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [118]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [653]}},
   'weight': 2}),
 ('600',
  'payé',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [149]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [684]}},
   'weight': 2}),
 ('www',
  'avs_ai',
  {'paths': {'22': {'word_positions': [240]}, '26': {'word_positions': [238]}},
   'weight': 2}),
 ('www',
  'ahv_iv',
  {'paths': {'22': {'word_positions': [236]}, '26': {'word_positions': [234]}},
   'weight': 2}),
 ('581270',
  '30003',
  {'paths': {'13': {'text_data': {'length': 313},
     'text_id': 13,
     'word_positions': [58]},
    '32': {'text_data': {'length': 328},
     'text_id': 32,
     'word_positions': [54]}},
   'weight': 2}),
 ('m_l',
  'indte_speciale',
  {'paths': {'13': {'word_positions': [167]}, '32': {'word_positions': [168]}},
   'weight': 2}),
 ('mw_afs',
  '34696_modification',
  {'paths': {'16': {'word_positions': [59]}, '4': {'word_positions': [59]}},
   'weight': 2}),
 ('irc',
  'reg',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [163, 170]}},
   'weight': 2}),
 ('à_la',
  'lpers',
  {'paths': {'0': {'word_positions': [363]}, '14': {'word_positions': [899]}},
   'weight': 2}),
 ('44',
  '4',
  {'paths': {'3': {'text_data': {'length': 157},
     'text_id': 3,
     'word_positions': [41, 104]}},
   'weight': 2}),
 ('nicole',
  'jenny',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [25]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [25]}},
   'weight': 2}),
 ('1015_lausanne',
  'n',
  {'paths': {'22': {'word_positions': [13]}, '26': {'word_positions': [13]}},
   'weight': 2}),
 ('epfl_et',
  'directive_sur',
  {'paths': {'0': {'word_positions': [387]}, '14': {'word_positions': [923]}},
   'weight': 2}),
 ('conservez',
  'ce',
  {'paths': {'21': {'text_data': {'length': 282},
     'text_id': 21,
     'word_positions': [273]},
    '32': {'text_data': {'length': 328},
     'text_id': 32,
     'word_positions': [318]}},
   'weight': 2}),
 ('especes',
  'pea',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [244]},
    '34': {'text_data': {'length': 490},
     'text_id': 34,
     'word_positions': [231]}},
   'weight': 2}),
 ('3_mois',
  'effective',
  {'paths': {'0': {'word_positions': [117]}, '14': {'word_positions': [652]}},
   'weight': 2}),
 ('tx',
  'r',
  {'paths': {'13': {'text_data': {'length': 313},
     'text_id': 13,
     'word_positions': [144]},
    '32': {'text_data': {'length': 328},
     'text_id': 32,
     'word_positions': [141]}},
   'weight': 2}),
 ('du_contrat',
  'est',
  {'paths': {'0': {'word_positions': [294]}, '14': {'word_positions': [829]}},
   'weight': 2}),
 ('polytechniolje',
  'federale',
  {'paths': {'29': {'text_data': {'length': 336},
     'text_id': 29,
     'word_positions': [32]},
    '36': {'text_data': {'length': 567},
     'text_id': 36,
     'word_positions': [174]}},
   'weight': 2}),
 ('concernant',
  'vous_pouvez',
  {'paths': {'11': {'word_positions': [387]}, '15': {'word_positions': [268]}},
   'weight': 2}),
 ('dessus',
  'désignée_en',
  {'paths': {'11': {'word_positions': [88]}, '34': {'word_positions': [87]}},
   'weight': 2}),
 ('dirigerez',
  'sur',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [93]},
    '34': {'text_data': {'length': 490},
     'text_id': 34,
     'word_positions': [92]}},
   'weight': 2}),
 ('mme',
  'carine',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [86]},
    '9': {'text_data': {'length': 451},
     'text_id': 9,
     'word_positions': [274]}},
   'weight': 2}),
 ('mme',
  'lahille',
  {'paths': {'8': {'text_data': {'length': 779},
     'text_id': 8,
     'word_positions': [73, 309]}},
   'weight': 2}),
 ('307',
  'net',
  {'paths': {'37': {'text_data': {'length': 349},
     'text_id': 37,
     'word_positions': [333]},
    '5': {'text_data': {'length': 349},
     'text_id': 5,
     'word_positions': [333]}},
   'weight': 2}),
 ('de',
  'nous',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [154]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [154]}},
   'weight': 2}),
 ('de',
  'rale_de',
  {'paths': {'16': {'word_positions': [34]}, '4': {'word_positions': [34]}},
   'weight': 2}),
 ('de',
  'marie_lahille',
  {'paths': {'9': {'word_positions': [353, 339]}}, 'weight': 2}),
 ('de',
  'ce',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [165]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [165]}},
   'weight': 2}),
 ('de',
  'procédure',
  {'paths': {'28': {'text_data': {'length': 103},
     'text_id': 28,
     'word_positions': [73, 100]}},
   'weight': 2}),
 ('de',
  'i_epfl',
  {'paths': {'0': {'word_positions': [397]}, '14': {'word_positions': [933]}},
   'weight': 2}),
 ('de',
  'changement',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [86]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [86]}},
   'weight': 2}),
 ('traitement',
  'vous_pouvez',
  {'paths': {'11': {'word_positions': [406]}, '15': {'word_positions': [287]}},
   'weight': 2}),
 ('carine',
  'bordeaux',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [87]},
    '9': {'text_data': {'length': 451},
     'text_id': 9,
     'word_positions': [275]}},
   'weight': 2}),
 ('543',
  '65',
  {'paths': {'29': {'text_data': {'length': 336},
     'text_id': 29,
     'word_positions': [304]},
    '36': {'text_data': {'length': 567},
     'text_id': 36,
     'word_positions': [524]}},
   'weight': 2}),
 ('70_780',
  '00_5',
  {'paths': {'2': {'word_positions': [197]}, '25': {'word_positions': [191]}},
   'weight': 2}),
 ('anthonin',
  'anthonin',
  {'paths': {'29': {'text_data': {'length': 336},
     'text_id': 29,
     'word_positions': [236]},
    '36': {'text_data': {'length': 567},
     'text_id': 36,
     'word_positions': [457]}},
   'weight': 2}),
 ('anthonin',
  'maya',
  {'paths': {'29': {'text_data': {'length': 336},
     'text_id': 29,
     'word_positions': [237]},
    '36': {'text_data': {'length': 567},
     'text_id': 36,
     'word_positions': [458]}},
   'weight': 2}),
 ('107',
  'cotisation_ac',
  {'paths': {'2': {'word_positions': [253]}, '7': {'word_positions': [165]}},
   'weight': 2}),
 ('vandergheynst_pour',
  'l_epfl',
  {'paths': {'14': {'word_positions': [802]}, '19': {'word_positions': [281]}},
   'weight': 2}),
 ('01_001',
  'f',
  {'paths': {'13': {'word_positions': [136]}, '21': {'word_positions': [126]}},
   'weight': 2}),
 ('epf',
  'opers_epf',
  {'paths': {'0': {'word_positions': [373]}, '14': {'word_positions': [909]}},
   'weight': 2}),
 ('olympe',
  '1500',
  {'paths': {'29': {'text_data': {'length': 336},
     'text_id': 29,
     'word_positions': [240]},
    '36': {'text_data': {'length': 567},
     'text_id': 36,
     'word_positions': [461]}},
   'weight': 2}),
 ('les',
  'données',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [105]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [105]}},
   'weight': 2}),
 ('ce',
  'contrat',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [243]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [778]}},
   'weight': 2}),
 ('ce',
  'document',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [166]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [166]}},
   'weight': 2}),
 ('l',
  'avs_al',
  {'paths': {'22': {'word_positions': [100]}, '26': {'word_positions': [100]}},
   'weight': 2}),
 ('l',
  'opérateur',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [263]},
    '9': {'text_data': {'length': 451},
     'text_id': 9,
     'word_positions': [423]}},
   'weight': 2}),
 ('l',
  'rh',
  {'paths': {'16': {'text_data': {'length': 200},
     'text_id': 16,
     'word_positions': [46]},
    '4': {'text_data': {'length': 200}, 'text_id': 4, 'word_positions': [46]}},
   'weight': 2}),
 ('l',
  'état',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [113]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [113]}},
   'weight': 2}),
 ('l',
  're',
  {'paths': {'32': {'text_data': {'length': 328},
     'text_id': 32,
     'word_positions': [2, 292]}},
   'weight': 2}),
 ('soit',
  'pour_information',
  {'paths': {'6': {'word_positions': [767]}, '9': {'word_positions': [375]}},
   'weight': 2}),
 ('761',
  'c_s',
  {'paths': {'13': {'word_positions': [190]}, '32': {'word_positions': [192]}},
   'weight': 2}),
 ('birth',
  'date',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [76]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [610]}},
   'weight': 2}),
 ('93',
  '0',
  {'paths': {'8': {'text_data': {'length': 779},
     'text_id': 8,
     'word_positions': [402, 418]}},
   'weight': 2}),
 ('cochant',
  'la_case',
  {'paths': {'11': {'word_positions': [436]}, '15': {'word_positions': [318]}},
   'weight': 2}),
 ('p',
  '100',
  {'paths': {'13': {'text_data': {'length': 313},
     'text_id': 13,
     'word_positions': [249]},
    '32': {'text_data': {'length': 328},
     'text_id': 32,
     'word_positions': [250]}},
   'weight': 2}),
 ('p',
  'ircantec',
  {'paths': {'20': {'text_data': {'length': 278},
     'text_id': 20,
     'word_positions': [215]},
    '21': {'text_data': {'length': 282},
     'text_id': 21,
     'word_positions': [211]}},
   'weight': 2}),
 ('p',
  'cumul_du',
  {'paths': {'20': {'word_positions': [219]}, '21': {'word_positions': [215]}},
   'weight': 2}),
 ('sont',
  'obligat01res',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [277]},
    '15': {'text_data': {'length': 388},
     'text_id': 15,
     'word_positions': [160]}},
   'weight': 2}),
 ('9',
  '55',
  {'paths': {'2': {'text_data': {'length': 345},
     'text_id': 2,
     'word_positions': [313]},
    '25': {'text_data': {'length': 339},
     'text_id': 25,
     'word_positions': [307]}},
   'weight': 2}),
 ('questions',
  'sur_le',
  {'paths': {'8': {'word_positions': [688, 626]}}, 'weight': 2}),
 ('fl',
  'ressources_humaines',
  {'paths': {'16': {'word_positions': [1]}, '4': {'word_positions': [1]}},
   'weight': 2}),
 ('350_00',
  '100_00',
  {'paths': {'2': {'word_positions': [85]}, '25': {'word_positions': [85]}},
   'weight': 2}),
 ('juillet',
  '2014',
  {'paths': {'1': {'text_data': {'length': 175},
     'text_id': 1,
     'word_positions': [79]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [450]}},
   'weight': 2}),
 ('juillet',
  '2013',
  {'paths': {'14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [272]},
    '31': {'text_data': {'length': 181},
     'text_id': 31,
     'word_positions': [83]}},
   'weight': 2}),
 ('joint',
  'votre',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [48]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [48]}},
   'weight': 2}),
 ('rh',
  'téléphone_4121',
  {'paths': {'0': {'word_positions': [5]}, '19': {'word_positions': [7]}},
   'weight': 2}),
 ('rh',
  'bâtiment',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [7]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [7]}},
   'weight': 2}),
 ('lors',
  'd_une',
  {'paths': {'22': {'word_positions': [91]}, '26': {'word_positions': [91]}},
   'weight': 2}),
 ('lors',
  'de_la',
  {'paths': {'0': {'word_positions': [249]}, '14': {'word_positions': [784]}},
   'weight': 2}),
 ('412169311',
  '11_école',
  {'paths': {'16': {'word_positions': [8]}, '4': {'word_positions': [8]}},
   'weight': 2}),
 ('releve',
  'en',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [175]},
    '34': {'text_data': {'length': 490},
     'text_id': 34,
     'word_positions': [171]}},
   'weight': 2}),
 ('139',
  '230',
  {'paths': {'29': {'text_data': {'length': 336},
     'text_id': 29,
     'word_positions': [269]},
    '36': {'text_data': {'length': 567},
     'text_id': 36,
     'word_positions': [481]}},
   'weight': 2}),
 ('139',
  '25',
  {'paths': {'2': {'text_data': {'length': 345},
     'text_id': 2,
     'word_positions': [116]},
    '25': {'text_data': {'length': 339},
     'text_id': 25,
     'word_positions': [110]}},
   'weight': 2}),
 ('139',
  '60',
  {'paths': {'37': {'text_data': {'length': 349},
     'text_id': 37,
     'word_positions': [110]},
    '7': {'text_data': {'length': 355},
     'text_id': 7,
     'word_positions': [116]}},
   'weight': 2}),
 ('09',
  '2016',
  {'paths': {'37': {'text_data': {'length': 349},
     'text_id': 37,
     'word_positions': [65]},
    '5': {'text_data': {'length': 349}, 'text_id': 5, 'word_positions': [65]}},
   'weight': 2}),
 ('interet',
  'et',
  {'paths': {'21': {'text_data': {'length': 282},
     'text_id': 21,
     'word_positions': [263]},
    '24': {'text_data': {'length': 69},
     'text_id': 24,
     'word_positions': [52]}},
   'weight': 2}),
 ('adedl',
  'ire_salaire',
  {'paths': {'13': {'word_positions': [146]}, '32': {'word_positions': [147]}},
   'weight': 2}),
 ('agence_actuelle',
  '00104',
  {'paths': {'11': {'word_positions': [34]}, '15': {'word_positions': [36]}},
   'weight': 2}),
 ('qu',
  'à',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [338]},
    '15': {'text_data': {'length': 388},
     'text_id': 15,
     'word_positions': [221]}},
   'weight': 2}),
 ('qu',
  'elles',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [109]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [109]}},
   'weight': 2}),
 ('art',
  '12_lpers',
  {'paths': {'0': {'word_positions': [236]}, '14': {'word_positions': [771]}},
   'weight': 2}),
 ('4933',
  '37',
  {'paths': {'37': {'text_data': {'length': 349},
     'text_id': 37,
     'word_positions': [180]},
    '5': {'text_data': {'length': 349},
     'text_id': 5,
     'word_positions': [180]}},
   'weight': 2}),
 ('les_bains',
  'par',
  {'paths': {'9': {'word_positions': [251, 29]}}, 'weight': 2}),
 ('les_bains',
  'bgw',
  {'paths': {'11': {'word_positions': [38]}, '15': {'word_positions': [40]}},
   'weight': 2}),
 ('les_bains',
  'dec_annemasse',
  {'paths': {'11': {'word_positions': [62]}, '15': {'word_positions': [64]}},
   'weight': 2}),
 ('les_bains',
  'lausanne_le',
  {'paths': {'14': {'word_positions': [268]}, '31': {'word_positions': [79]}},
   'weight': 2}),
 ('infirmier',
  'd_e',
  {'paths': {'13': {'word_positions': [46]}, '32': {'word_positions': [40]}},
   'weight': 2}),
 ('sous',
  'le',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [57]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [57]}},
   'weight': 2}),
 ('sous',
  'des',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [357]},
    '15': {'text_data': {'length': 388},
     'text_id': 15,
     'word_positions': [240]}},
   'weight': 2}),
 ('40',
  'brut',
  {'paths': {'2': {'text_data': {'length': 345},
     'text_id': 2,
     'word_positions': [138]},
    '25': {'text_data': {'length': 339},
     'text_id': 25,
     'word_positions': [132]}},
   'weight': 2}),
 ('nous_vous',
  'prie_prions',
  {'paths': {'11': {'word_positions': [67]}, '15': {'word_positions': [69]}},
   'weight': 2}),
 ('nous_vous',
  'prions',
  {'paths': {'22': {'word_positions': [178]}, '26': {'word_positions': [178]}},
   'weight': 2}),
 ('nous_vous',
  'remercions',
  {'paths': {'22': {'word_positions': [152]}, '26': {'word_positions': [152]}},
   'weight': 2}),
 ('t',
  'pour_vous',
  {'paths': {'13': {'word_positions': [294]}, '32': {'word_positions': [309]}},
   'weight': 2}),
 ('t',
  'e',
  {'paths': {'13': {'text_data': {'length': 313},
     'text_id': 13,
     'word_positions': [292]},
    '32': {'text_data': {'length': 328},
     'text_id': 32,
     'word_positions': [307]}},
   'weight': 2}),
 ('ce_accident',
  'afpallocations',
  {'paths': {'36': {'word_positions': [564, 158]}}, 'weight': 2}),
 ('638',
  '507_cotisation',
  {'paths': {'36': {'word_positions': [116]}, '7': {'word_positions': [325]}},
   'weight': 2}),
 ('sa_ch5609000000124743854',
  '7',
  {'paths': {'2': {'word_positions': [338]}, '25': {'word_positions': [332]}},
   'weight': 2}),
 ('étrangers',
  'ou',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [121]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [121]}},
   'weight': 2}),
 ('io',
  'ue',
  {'paths': {'16': {'text_data': {'length': 200},
     'text_id': 16,
     'word_positions': [13]},
    '4': {'text_data': {'length': 200}, 'text_id': 4, 'word_positions': [13]}},
   'weight': 2}),
 ('jean_leger',
  'bhg',
  {'paths': {'11': {'word_positions': [57]}, '15': {'word_positions': [59]}},
   'weight': 2}),
 ('60',
  '00',
  {'paths': {'29': {'text_data': {'length': 336},
     'text_id': 29,
     'word_positions': [285]},
    '36': {'text_data': {'length': 567},
     'text_id': 36,
     'word_positions': [499]}},
   'weight': 2}),
 ('ur',
  'l_epfl',
  {'paths': {'14': {'word_positions': [344]}, '31': {'word_positions': [155]}},
   'weight': 2}),
 ('resources_manager',
  'original',
  {'paths': {'0': {'word_positions': [285]}, '14': {'word_positions': [821]}},
   'weight': 2}),
 ('l_employé',
  'the_employee',
  {'paths': {'0': {'word_positions': [273]}, '14': {'word_positions': [809]}},
   'weight': 2}),
 ('vous_pouvez',
  'également',
  {'paths': {'11': {'word_positions': [389]}, '15': {'word_positions': [270]}},
   'weight': 2}),
 ('922',
  '407',
  {'paths': {'29': {'text_data': {'length': 336},
     'text_id': 29,
     'word_positions': [306]},
    '36': {'text_data': {'length': 567},
     'text_id': 36,
     'word_positions': [526]}},
   'weight': 2}),
 ('12_15',
  '2_760',
  {'paths': {'7': {'word_positions': [121, 100]}}, 'weight': 2}),
 ('correspondent_à',
  '100_41',
  {'paths': {'0': {'word_positions': [136]}, '14': {'word_positions': [671]}},
   'weight': 2}),
 ('du_client',
  '1',
  {'paths': {'11': {'word_positions': [472]}, '15': {'word_positions': [346]}},
   'weight': 2}),
 ('5267',
  '0600',
  {'paths': {'29': {'text_data': {'length': 336},
     'text_id': 29,
     'word_positions': [243]},
    '36': {'text_data': {'length': 567},
     'text_id': 36,
     'word_positions': [464]}},
   'weight': 2}),
 ('messieurs',
  'vous',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [44]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [44]}},
   'weight': 2}),
 ('ci',
  'dessus',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [87]},
    '34': {'text_data': {'length': 490},
     'text_id': 34,
     'word_positions': [86]}},
   'weight': 2}),
 ('ci',
  'joint',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [47]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [47]}},
   'weight': 2}),
 ('re',
  'atif',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [381]},
    '34': {'text_data': {'length': 490},
     'text_id': 34,
     'word_positions': [368]}},
   'weight': 2}),
 ('re',
  'des',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [119]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [119]}},
   'weight': 2}),
 ('lytechn',
  'io',
  {'paths': {'16': {'text_data': {'length': 200},
     'text_id': 16,
     'word_positions': [12]},
    '4': {'text_data': {'length': 200}, 'text_id': 4, 'word_positions': [12]}},
   'weight': 2}),
 ('payé',
  'en_13',
  {'paths': {'0': {'word_positions': [150]}, '14': {'word_positions': [685]}},
   'weight': 2}),
 ('112',
  '057',
  {'paths': {'2': {'text_data': {'length': 345},
     'text_id': 2,
     'word_positions': [328]},
    '25': {'text_data': {'length': 339},
     'text_id': 25,
     'word_positions': [322]}},
   'weight': 2}),
 ('park',
  'h',
  {'paths': {'8': {'text_data': {'length': 779},
     'text_id': 8,
     'word_positions': [544, 549]}},
   'weight': 2}),
 ('garage',
  'park',
  {'paths': {'8': {'text_data': {'length': 779},
     'text_id': 8,
     'word_positions': [543, 548]}},
   'weight': 2}),
 ('cas',
  'de',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [85]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [85]}},
   'weight': 2}),
 ('vos',
  'compte',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [284]},
    '15': {'text_data': {'length': 388},
     'text_id': 15,
     'word_positions': [167]}},
   'weight': 2}),
 ('861',
  '00_maya',
  {'paths': {'2': {'word_positions': [134]}, '25': {'word_positions': [128]}},
   'weight': 2}),
 ('date_d',
  'edition',
  {'paths': {'36': {'word_positions': [50, 210]}}, 'weight': 2}),
 ('avsl',
  'v',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [2]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [3]}},
   'weight': 2}),
 ('les_meilleures',
  'pour',
  {'paths': {'1': {'word_positions': [150]}, '14': {'word_positions': [520]}},
   'weight': 2}),
 ('les_meilleures',
  'ur',
  {'paths': {'14': {'word_positions': [343]}, '31': {'word_positions': [154]}},
   'weight': 2}),
 ('les_meilleures',
  'o',
  {'paths': {'16': {'word_positions': [177]}, '4': {'word_positions': [177]}},
   'weight': 2}),
 ('vos_droits',
  'une',
  {'paths': {'0': {'word_positions': [163]}, '14': {'word_positions': [698]}},
   'weight': 2}),
 ('vos_droits',
  'conservez',
  {'paths': {'21': {'word_positions': [272]}, '32': {'word_positions': [317]}},
   'weight': 2}),
 ('avril',
  '2015',
  {'paths': {'36': {'text_data': {'length': 567},
     'text_id': 36,
     'word_positions': [25, 197]}},
   'weight': 2}),
 ('allowance',
  's',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [182]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [717]}},
   'weight': 2}),
 ('757',
  'net',
  {'paths': {'36': {'text_data': {'length': 567},
     'text_id': 36,
     'word_positions': [130]},
    '7': {'text_data': {'length': 355},
     'text_id': 7,
     'word_positions': [339]}},
   'weight': 2}),
 ('n_réf',
  'mw_afs',
  {'paths': {'16': {'word_positions': [57]}, '4': {'word_positions': [57]}},
   'weight': 2}),
 ('787',
  '30',
  {'paths': {'37': {'text_data': {'length': 349},
     'text_id': 37,
     'word_positions': [252]},
    '5': {'text_data': {'length': 349},
     'text_id': 5,
     'word_positions': [252]}},
   'weight': 2}),
 ('periode',
  'taux_base',
  {'paths': {'36': {'word_positions': [221, 61]}}, 'weight': 2}),
 ('nom',
  'diffère',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [140]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [140]}},
   'weight': 2}),
 ('nom',
  'lahille',
  {'paths': {'13': {'text_data': {'length': 313},
     'text_id': 13,
     'word_positions': [34]},
    '21': {'text_data': {'length': 282},
     'text_id': 21,
     'word_positions': [21]}},
   'weight': 2}),
 ('1250_393',
  '657_cotisation',
  {'paths': {'37': {'word_positions': [244]}, '5': {'word_positions': [244]}},
   'weight': 2}),
 ('000',
  '00',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [732]},
    '9': {'text_data': {'length': 451},
     'text_id': 9,
     'word_positions': [359]}},
   'weight': 2}),
 ('000',
  'ecole_polytechnique',
  {'paths': {'22': {'word_positions': [20]}, '26': {'word_positions': [20]}},
   'weight': 2}),
 ('annual',
  'salary',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [155]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [690]}},
   'weight': 2}),
 ('0898',
  '6',
  {'paths': {'37': {'text_data': {'length': 349},
     'text_id': 37,
     'word_positions': [305]},
    '5': {'text_data': {'length': 349},
     'text_id': 5,
     'word_positions': [305]}},
   'weight': 2}),
 ('0600_4',
  '607_cotisation',
  {'paths': {'37': {'word_positions': [193]}, '5': {'word_positions': [193]}},
   'weight': 2}),
 ('montant',
  'à_payer',
  {'paths': {'8': {'word_positions': [170, 158]}}, 'weight': 2}),
 ('administratives',
  'avec',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [77]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [77]}},
   'weight': 2}),
 ('the',
  'laws',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [339]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [875]}},
   'weight': 2}),
 ('societe_generale',
  'demande_de',
  {'paths': {'11': {'word_positions': [1]}, '34': {'word_positions': [1]}},
   'weight': 2}),
 ('societe_generale',
  's_a',
  {'paths': {'11': {'word_positions': [482]}, '15': {'word_positions': [362]}},
   'weight': 2}),
 ('maya',
  'olympe',
  {'paths': {'29': {'text_data': {'length': 336},
     'text_id': 29,
     'word_positions': [239]},
    '36': {'text_data': {'length': 567},
     'text_id': 36,
     'word_positions': [460]}},
   'weight': 2}),
 ('maya',
  'maya',
  {'paths': {'29': {'text_data': {'length': 336},
     'text_id': 29,
     'word_positions': [238]},
    '36': {'text_data': {'length': 567},
     'text_id': 36,
     'word_positions': [459]}},
   'weight': 2}),
 ('je',
  'nous_vous',
  {'paths': {'11': {'word_positions': [65]}, '15': {'word_positions': [67]}},
   'weight': 2}),
 ('370',
  '389_83',
  {'paths': {'29': {'word_positions': [271]}, '36': {'word_positions': [484]}},
   'weight': 2}),
 ('jenny',
  'rappo',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [26]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [26]}},
   'weight': 2}),
 ('409',
  '207',
  {'paths': {'2': {'text_data': {'length': 345},
     'text_id': 2,
     'word_positions': [154, 240]}},
   'weight': 2}),
 ('vez',
  'ce',
  {'paths': {'13': {'text_data': {'length': 313},
     'text_id': 13,
     'word_positions': [304]},
    '20': {'text_data': {'length': 278},
     'text_id': 20,
     'word_positions': [269]}},
   'weight': 2}),
 ('bulletln',
  'de_salaire',
  {'paths': {'13': {'word_positions': [16]}, '32': {'word_positions': [12]}},
   'weight': 2}),
 ('susmentionné',
  'que',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [62]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [62]}},
   'weight': 2}),
 ('bulletin',
  'n',
  {'paths': {'28': {'text_data': {'length': 103},
     'text_id': 28,
     'word_positions': [62, 84]}},
   'weight': 2}),
 ('numéro',
  'actuel',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [116]},
    '15': {'text_data': {'length': 388},
     'text_id': 15,
     'word_positions': [120]}},
   'weight': 2}),
 ('numéro',
  'd',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [59]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [59]}},
   'weight': 2}),
 ('dette_sociale',
  '050',
  {'paths': {'13': {'word_positions': [188]}, '32': {'word_positions': [190]}},
   'weight': 2}),
 ('rapport',
  'à',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [143]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [143]}},
   'weight': 2}),
 ('epfl_ch',
  '00',
  {'paths': {'16': {'word_positions': [49]}, '4': {'word_positions': [49]}},
   'weight': 2}),
 ('epfl_ch',
  'federale',
  {'paths': {'0': {'word_positions': [29]}, '14': {'word_positions': [566]}},
   'weight': 2}),
 ('epfl_ch',
  'monsieur',
  {'paths': {'1': {'word_positions': [45]}, '31': {'word_positions': [49]}},
   'weight': 2}),
 ('dated',
  'and',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [319]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [855]}},
   'weight': 2}),
 ('cadre',
  'relative',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [360]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [896]}},
   'weight': 2}),
 ('ahv',
  'avsl',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [1]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [2]}},
   'weight': 2}),
 ('ces_droits',
  'peuvent',
  {'paths': {'11': {'word_positions': [443]}, '15': {'word_positions': [325]}},
   'weight': 2}),
 ('precedence',
  'this',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [326]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [862]}},
   'weight': 2}),
 ('bâtiment',
  'inn',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [8]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [8]}},
   'weight': 2}),
 ('second',
  'original_copy',
  {'paths': {'0': {'word_positions': [309]}, '14': {'word_positions': [845]}},
   'weight': 2}),
 ('french_text',
  'takes',
  {'paths': {'0': {'word_positions': [324]}, '14': {'word_positions': [860]}},
   'weight': 2}),
 ('gmf',
  'assurances',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [359, 365]}},
   'weight': 2}),
 ('avs_ai',
  'info',
  {'paths': {'22': {'word_positions': [242]}, '26': {'word_positions': [240]}},
   'weight': 2}),
 ('avs_ai',
  'insurance',
  {'paths': {'22': {'word_positions': [211]}, '26': {'word_positions': [211]}},
   'weight': 2}),
 ('avec',
  'l_avs',
  {'paths': {'22': {'word_positions': [78]}, '26': {'word_positions': [78]}},
   'weight': 2}),
 ('prospection',
  'comerciale',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [433]},
    '34': {'text_data': {'length': 490},
     'text_id': 34,
     'word_positions': [419]}},
   'weight': 2}),
 ('professional',
  'and',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [219]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [754]}},
   'weight': 2}),
 ('professional',
  'accidents_délai',
  {'paths': {'0': {'word_positions': [222]}, '14': {'word_positions': [757]}},
   'weight': 2}),
 ('04_15',
  '73_675',
  {'paths': {'36': {'word_positions': [358, 365]}}, 'weight': 2}),
 ('04_15',
  '2_760',
  {'paths': {'36': {'word_positions': [288, 275]}}, 'weight': 2}),
 ('ou_le',
  'regist',
  {'paths': {'22': {'word_positions': [117]}, '26': {'word_positions': [117]}},
   'weight': 2}),
 ('le',
  'double',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [291]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [826]}},
   'weight': 2}),
 ('le',
  '1',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [29]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [29]}},
   'weight': 2}),
 ('le',
  'i',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [462]},
    '19': {'text_data': {'length': 385},
     'text_id': 19,
     'word_positions': [379]}},
   'weight': 2}),
 ('le',
  'numéro',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [58]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [58]}},
   'weight': 2}),
 ('amin',
  'ricaud_date',
  {'paths': {'14': {'word_positions': [186, 366]}}, 'weight': 2}),
 ('que_l',
  'orthographe',
  {'paths': {'22': {'word_positions': [137]}, '26': {'word_positions': [137]}},
   'weight': 2}),
 ('original_copy',
  'to',
  {'paths': {'0': {'word_positions': [306]}, '14': {'word_positions': [841]}},
   'weight': 2}),
 ('original_copy',
  'to_be',
  {'paths': {'0': {'word_positions': [311]}, '14': {'word_positions': [847]}},
   'weight': 2}),
 ('907',
  'charges_sociales',
  {'paths': {'2': {'word_positions': [214]}, '25': {'word_positions': [208]}},
   'weight': 2}),
 ('ainsi',
  'qu',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [337]},
    '15': {'text_data': {'length': 388},
     'text_id': 15,
     'word_positions': [220]}},
   'weight': 2}),
 ('document',
  'sont',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [276]},
    '34': {'text_data': {'length': 490},
     'text_id': 34,
     'word_positions': [266]}},
   'weight': 2}),
 ('document',
  'en',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [167]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [167]}},
   'weight': 2}),
 ('construed',
  'in',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [335]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [871]}},
   'weight': 2}),
 ('8',
  '659',
  {'paths': {'37': {'text_data': {'length': 349},
     'text_id': 37,
     'word_positions': [146]},
    '5': {'text_data': {'length': 349},
     'text_id': 5,
     'word_positions': [146]}},
   'weight': 2}),
 ('8',
  'juillet',
  {'paths': {'1': {'text_data': {'length': 175},
     'text_id': 1,
     'word_positions': [78]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [449]}},
   'weight': 2}),
 ('8',
  '40',
  {'paths': {'2': {'text_data': {'length': 345},
     'text_id': 2,
     'word_positions': [137]},
    '25': {'text_data': {'length': 339},
     'text_id': 25,
     'word_positions': [131]}},
   'weight': 2}),
 ('8',
  '543',
  {'paths': {'29': {'text_data': {'length': 336},
     'text_id': 29,
     'word_positions': [303]},
    '36': {'text_data': {'length': 567},
     'text_id': 36,
     'word_positions': [523]}},
   'weight': 2}),
 ('en',
  'pourcentage',
  {'paths': {'8': {'text_data': {'length': 779},
     'text_id': 8,
     'word_positions': [433, 495]}},
   'weight': 2}),
 ('en',
  'ligne',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [176]},
    '34': {'text_data': {'length': 490},
     'text_id': 34,
     'word_positions': [172]}},
   'weight': 2}),
 ('en',
  'cas',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [84]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [84]}},
   'weight': 2}),
 ('en',
  'restant',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [168]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [168]}},
   'weight': 2}),
 ('en',
  'valeur',
  {'paths': {'8': {'text_data': {'length': 779},
     'text_id': 8,
     'word_positions': [425, 493]}},
   'weight': 2}),
 ('en',
  'cochant',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [435]},
    '15': {'text_data': {'length': 388},
     'text_id': 15,
     'word_positions': [317]}},
   'weight': 2}),
 ('bleue',
  'visa',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [219]},
    '34': {'text_data': {'length': 490},
     'text_id': 34,
     'word_positions': [207]}},
   'weight': 2}),
 ('conser',
  'vez',
  {'paths': {'13': {'text_data': {'length': 313},
     'text_id': 13,
     'word_positions': [303]},
    '20': {'text_data': {'length': 278},
     'text_id': 20,
     'word_positions': [268]}},
   'weight': 2}),
 ('23_juin',
  '2015',
  {'paths': {'16': {'word_positions': [83]}, '4': {'word_positions': [83]}},
   'weight': 2}),
 ('340',
  '000',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [19]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [19]}},
   'weight': 2}),
 ('variation',
  'en',
  {'paths': {'8': {'text_data': {'length': 779},
     'text_id': 8,
     'word_positions': [424, 432]}},
   'weight': 2}),
 ('p_deplaf',
  'fonds',
  {'paths': {'20': {'word_positions': [211]}, '21': {'word_positions': [207]}},
   'weight': 2}),
 ('p_deplaf',
  '540',
  {'paths': {'13': {'word_positions': [238]}, '32': {'word_positions': [239]}},
   'weight': 2}),
 ('fr',
  '74200_thonon',
  {'paths': {'14': {'word_positions': [264]}, '31': {'word_positions': [75]}},
   'weight': 2}),
 ('effectuées_sur',
  'mes_nos',
  {'paths': {'11': {'word_positions': [103]}, '15': {'word_positions': [107]}},
   'weight': 2}),
 ('il',
  'se',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [133]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [133]}},
   'weight': 2}),
 ('il',
  'ressources_humaines',
  {'paths': {'19': {'word_positions': [1]}, '31': {'word_positions': [1]}},
   'weight': 2}),
 ('enj',
  'amin',
  {'paths': {'14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [185, 365]}},
   'weight': 2}),
 ('he',
  'hero_de',
  {'paths': {'34': {'word_positions': [164, 150]}}, 'weight': 2}),
 ('g_deductible',
  'c_s',
  {'paths': {'20': {'word_positions': [171]}, '21': {'word_positions': [171]}},
   'weight': 2}),
 ('g_deductible',
  '510',
  {'paths': {'13': {'word_positions': [194]}, '32': {'word_positions': [196]}},
   'weight': 2}),
 ('151',
  'm',
  {'paths': {'13': {'text_data': {'length': 313},
     'text_id': 13,
     'word_positions': [105]},
    '20': {'text_data': {'length': 278},
     'text_id': 20,
     'word_positions': [101]}},
   'weight': 2}),
 ('prélèvement',
  'service',
  {'paths': {'8': {'text_data': {'length': 779},
     'text_id': 8,
     'word_positions': [622, 635]}},
   'weight': 2}),
 ('1',
  '00',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [611]},
    '9': {'text_data': {'length': 451},
     'text_id': 9,
     'word_positions': [437]}},
   'weight': 2}),
 ('1',
  'indte_speciale',
  {'paths': {'20': {'word_positions': [153]}, '21': {'word_positions': [152]}},
   'weight': 2}),
 ('1',
  'depuis',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [227]},
    '9': {'text_data': {'length': 451},
     'text_id': 9,
     'word_positions': [386]}},
   'weight': 2}),
 ('1',
  '3',
  {'paths': {'20': {'text_data': {'length': 278},
     'text_id': 20,
     'word_positions': [116]},
    '6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [231]}},
   'weight': 2}),
 ('1',
  'octobre',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [30]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [30]}},
   'weight': 2}),
 ('1',
  '5110912015',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [331, 350]}},
   'weight': 2}),
 ('nous',
  'signaler',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [155]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [155]}},
   'weight': 2}),
 ('cotisation_frais',
  'avs_emp',
  {'paths': {'2': {'word_positions': [243]}, '7': {'word_positions': [253]}},
   'weight': 2}),
 ('ou_la',
  'perte',
  {'paths': {'22': {'word_positions': [162]}, '26': {'word_positions': [162]}},
   'weight': 2}),
 ('leman',
  'agence_actuelle',
  {'paths': {'11': {'word_positions': [32]}, '15': {'word_positions': [34]}},
   'weight': 2}),
 ('européenne',
  'ces',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [351]},
    '15': {'text_data': {'length': 388},
     'text_id': 15,
     'word_positions': [234]}},
   'weight': 2}),
 ('nee_grade',
  'infirmier',
  {'paths': {'13': {'word_positions': [45]}, '32': {'word_positions': [39]}},
   'weight': 2}),
 ('berne',
  'le',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [28]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [28]}},
   'weight': 2}),
 ('auprès',
  'de_l',
  {'paths': {'11': {'word_positions': [447]}, '34': {'word_positions': [433]}},
   'weight': 2}),
 ('auprès',
  'de_la',
  {'paths': {'11': {'word_positions': [82]}, '15': {'word_positions': [84]}},
   'weight': 2}),
 ('mw',
  'ds',
  {'paths': {'1': {'text_data': {'length': 175},
     'text_id': 1,
     'word_positions': [55]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [419]}},
   'weight': 2}),
 ('mw',
  'cs',
  {'paths': {'14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [241]},
    '31': {'text_data': {'length': 181},
     'text_id': 31,
     'word_positions': [59]}},
   'weight': 2}),
 ('emp_04',
  '14_70',
  {'paths': {'25': {'word_positions': [315, 302]}}, 'weight': 2}),
 ('emp_04',
  '16_75',
  {'paths': {'37': {'word_positions': [312, 325]}}, 'weight': 2}),
 ('à_payer',
  '7_724',
  {'paths': {'37': {'word_positions': [336]}, '5': {'word_positions': [336]}},
   'weight': 2}),
 ('à_payer',
  '7',
  {'paths': {'2': {'word_positions': [332]}, '25': {'word_positions': [326]}},
   'weight': 2}),
 ('211',
  '25',
  {'paths': {'36': {'text_data': {'length': 567},
     'text_id': 36,
     'word_positions': [135, 141]}},
   'weight': 2}),
 ('tire',
  'ces_informations',
  {'paths': {'22': {'word_positions': [124]}, '26': {'word_positions': [124]}},
   'weight': 2}),
 ('i_epfl',
  'site_web',
  {'paths': {'0': {'word_positions': [399]}, '14': {'word_positions': [935]}},
   'weight': 2}),
 ('41216931111',
  'école',
  {'paths': {'1': {'text_data': {'length': 175},
     'text_id': 1,
     'word_positions': [8]},
    '31': {'text_data': {'length': 181},
     'text_id': 31,
     'word_positions': [8]}},
   'weight': 2}),
 ('universitaire',
  'av',
  {'paths': {'13': {'text_data': {'length': 313},
     'text_id': 13,
     'word_positions': [29]},
    '21': {'text_data': {'length': 282},
     'text_id': 21,
     'word_positions': [16]}},
   'weight': 2}),
 ('titulaires_si',
  'compte',
  {'paths': {'11': {'word_positions': [478]}, '15': {'word_positions': [357]}},
   'weight': 2}),
 ('ordonnance',
  'sur_le',
  {'paths': {'0': {'word_positions': [366]}, '14': {'word_positions': [902]}},
   'weight': 2}),
 ('salutations',
  'distinguées',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [186]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [186]}},
   'weight': 2}),
 ('posteinance',
  'sa_ch5609000000124743854',
  {'paths': {'25': {'word_positions': [330]}, '37': {'word_positions': [340]}},
   'weight': 2}),
 ('mesdames',
  'et',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [42]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [42]}},
   'weight': 2}),
 ('statistiques_et',
  'patrimoniales',
  {'paths': {'11': {'word_positions': [315]}, '15': {'word_positions': [198]}},
   'weight': 2}),
 ('tout',
  'renseignement',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [174]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [174]}},
   'weight': 2}),
 ('également',
  'vous_opposer',
  {'paths': {'11': {'word_positions': [390]}, '15': {'word_positions': [271]}},
   'weight': 2}),
 ('jazz',
  'bleue',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [218]},
    '34': {'text_data': {'length': 490},
     'text_id': 34,
     'word_positions': [206]}},
   'weight': 2}),
 ('rue',
  'vallon',
  {'paths': {'8': {'text_data': {'length': 779},
     'text_id': 8,
     'word_positions': [54, 717]}},
   'weight': 2}),
 ('suva_emp',
  '08_16',
  {'paths': {'5': {'word_positions': [298, 285]}}, 'weight': 2}),
 ('suva_emp',
  '12_14',
  {'paths': {'2': {'word_positions': [281, 294]}}, 'weight': 2}),
 ('suva_emp',
  '12_15',
  {'paths': {'7': {'word_positions': [291, 304]}}, 'weight': 2}),
 ('563',
  '307_cotisation',
  {'paths': {'2': {'word_positions': [315]}, '25': {'word_positions': [309]}},
   'weight': 2}),
 ('comerciale',
  'en',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [434]},
    '34': {'text_data': {'length': 490},
     'text_id': 34,
     'word_positions': [420]}},
   'weight': 2}),
 ('08_16',
  '2_760',
  {'paths': {'5': {'word_positions': [115, 94]}}, 'weight': 2}),
 ('contractuels_établis',
  'dans',
  {'paths': {'11': {'word_positions': [343]}, '15': {'word_positions': [226]}},
   'weight': 2}),
 ('du_miroir',
  '74500_maxilly',
  {'paths': {'11': {'word_positions': [28]}, '15': {'word_positions': [30]}},
   'weight': 2}),
 ('du_miroir',
  'le_chalet',
  {'paths': {'29': {'word_positions': [27]}, '36': {'word_positions': [169]}},
   'weight': 2}),
 ('du_miroir',
  '74500',
  {'paths': {'34': {'word_positions': [27]}, '9': {'word_positions': [316]}},
   'weight': 2}),
 ('giraud',
  'nom',
  {'paths': {'13': {'text_data': {'length': 313},
     'text_id': 13,
     'word_positions': [33]},
    '21': {'text_data': {'length': 282},
     'text_id': 21,
     'word_positions': [20]}},
   'weight': 2}),
 ('sans_exception',
  'effectuées_sur',
  {'paths': {'11': {'word_positions': [101]}, '15': {'word_positions': [105]}},
   'weight': 2}),
 ('d_e',
  'cn_2894',
  {'paths': {'13': {'word_positions': [48]}, '32': {'word_positions': [42]}},
   'weight': 2}),
 ('éventuelle',
  'de',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [164]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [164]}},
   'weight': 2}),
 ('1500',
  '1000',
  {'paths': {'29': {'text_data': {'length': 336},
     'text_id': 29,
     'word_positions': [241]},
    '36': {'text_data': {'length': 567},
     'text_id': 36,
     'word_positions': [462]}},
   'weight': 2}),
 ('s_s',
  'maladie_p',
  {'paths': {'21': {'word_positions': [183]}, '32': {'word_positions': [222]}},
   'weight': 2}),
 ('belle',
  'marie',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [70]},
    '9': {'text_data': {'length': 451},
     'text_id': 9,
     'word_positions': [305]}},
   'weight': 2}),
 ('157',
  '057',
  {'paths': {'29': {'text_data': {'length': 336},
     'text_id': 29,
     'word_positions': [293]},
    '36': {'text_data': {'length': 567},
     'text_id': 36,
     'word_positions': [507]}},
   'weight': 2}),
 ('humaines',
  'l_employé',
  {'paths': {'16': {'word_positions': [183]}, '4': {'word_positions': [183]}},
   'weight': 2}),
 ('evian',
  'les_bains',
  {'paths': {'11': {'word_positions': [60]}, '15': {'word_positions': [62]}},
   'weight': 2}),
 ('affiliation',
  'with_publica',
  {'paths': {'0': {'word_positions': [204]}, '19': {'word_positions': [218]}},
   'weight': 2}),
 ('name',
  'birth',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [75]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [609]}},
   'weight': 2}),
 ('0311091201',
  '5',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [317, 334]}},
   'weight': 2}),
 ('suppression',
  're',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [380]},
    '34': {'text_data': {'length': 490},
     'text_id': 34,
     'word_positions': [367]}},
   'weight': 2}),
 ('0_50',
  '4',
  {'paths': {'2': {'word_positions': [251]}, '7': {'word_positions': [261]}},
   'weight': 2}),
 ('epp',
  '04_15',
  {'paths': {'36': {'word_positions': [293, 280]}}, 'weight': 2}),
 ('epp',
  '08_16',
  {'paths': {'5': {'word_positions': [103, 124]}}, 'weight': 2}),
 ('epp',
  '12_14',
  {'paths': {'2': {'word_positions': [130, 109]}}, 'weight': 2}),
 ('epp',
  '12_15',
  {'paths': {'7': {'word_positions': [130, 109]}}, 'weight': 2}),
 ('30',
  '0_50',
  {'paths': {'37': {'word_positions': [253]}, '5': {'word_positions': [253]}},
   'weight': 2}),
 ('précédent',
  'nous_vous',
  {'paths': {'22': {'word_positions': [150]}, '26': {'word_positions': [150]}},
   'weight': 2}),
 ('reporting',
  'to',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [99]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [633]}},
   'weight': 2}),
 ('307_cotisation',
  'risque_cp',
  {'paths': {'2': {'word_positions': [317]}, '25': {'word_positions': [311]}},
   'weight': 2}),
 ('avspassuran',
  'ce_vieillesse',
  {'paths': {'36': {'word_positions': [143, 548]}}, 'weight': 2}),
 ('03',
  '1_av',
  {'paths': {'11': {'word_positions': [53]}, '34': {'word_positions': [52]}},
   'weight': 2}),
 ('prelevement',
  'gmf',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [205, 364]}},
   'weight': 2}),
 ('art_41',
  'opers_epf',
  {'paths': {'0': {'word_positions': [187]}, '14': {'word_positions': [722]}},
   'weight': 2}),
 ('frais',
  'avs_emp',
  {'paths': {'29': {'word_positions': [110]}, '5': {'word_positions': [247]}},
   'weight': 2}),
 ('dans_votre',
  'in',
  {'paths': {'13': {'word_positions': [289]}, '32': {'word_positions': [304]}},
   'weight': 2}),
 ('mro',
  'de',
  {'paths': {'34': {'text_data': {'length': 490},
     'text_id': 34,
     'word_positions': [234, 244]}},
   'weight': 2}),
 ('produits',
  'et_services',
  {'paths': {'11': {'word_positions': [294]}, '15': {'word_positions': [177]}},
   'weight': 2}),
 ('code',
  'de',
  {'paths': {'28': {'text_data': {'length': 103},
     'text_id': 28,
     'word_positions': [72, 99]}},
   'weight': 2}),
 ('99',
  '850',
  {'paths': {'37': {'text_data': {'length': 349},
     'text_id': 37,
     'word_positions': [83]},
    '5': {'text_data': {'length': 349}, 'text_id': 5, 'word_positions': [83]}},
   'weight': 2}),
 ('ue',
  'bi',
  {'paths': {'16': {'text_data': {'length': 200},
     'text_id': 16,
     'word_positions': [14]},
    '4': {'text_data': {'length': 200}, 'text_id': 4, 'word_positions': [14]}},
   'weight': 2}),
 ('epfl',
  'l_employé',
  {'paths': {'0': {'word_positions': [271]}, '14': {'word_positions': [807]}},
   'weight': 2}),
 ('75_175',
  '00_5',
  {'paths': {'37': {'word_positions': [201]}, '5': {'word_positions': [201]}},
   'weight': 2}),
 ('3603',
  'pour_information',
  {'paths': {'13': {'word_positions': [211]}, '32': {'word_positions': [212]}},
   'weight': 2}),
 ('agence',
  'de_la',
  {'paths': {'11': {'word_positions': [450]}, '34': {'word_positions': [436]}},
   'weight': 2}),
 ('du_pillon',
  '16',
  {'paths': {'14': {'word_positions': [262]}, '31': {'word_positions': [73]}},
   'weight': 2}),
 ('à',
  'savoir',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [349]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [885]}},
   'weight': 2}),
 ('à',
  'votre',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [170]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [170]}},
   'weight': 2}),
 ('à',
  'ses_partenaires',
  {'paths': {'11': {'word_positions': [339]}, '15': {'word_positions': [222]}},
   'weight': 2}),
 ('à',
  'celle',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [144]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [144]}},
   'weight': 2}),
 ('500',
  '00',
  {'paths': {'9': {'text_data': {'length': 451},
     'text_id': 9,
     'word_positions': [128, 134]}},
   'weight': 2}),
 ('govemed',
  'by',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [332]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [868]}},
   'weight': 2}),
 ('sur',
  'vos',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [787, 903]}},
   'weight': 2}),
 ('sur',
  'leman',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [31]},
    '15': {'text_data': {'length': 388},
     'text_id': 15,
     'word_positions': [33]}},
   'weight': 2}),
 ('pour',
  'l_epfl',
  {'paths': {'1': {'word_positions': [151]}, '14': {'word_positions': [521]}},
   'weight': 2}),
 ('pour',
  'marie_lahille',
  {'paths': {'6': {'word_positions': [418, 734]}}, 'weight': 2}),
 ('pour',
  'tout',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [173]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [173]}},
   'weight': 2}),
 ('7_565',
  '73_675',
  {'paths': {'29': {'word_positions': [209, 194]}}, 'weight': 2}),
 ('et',
  'ordonnance',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [365]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [901]}},
   'weight': 2}),
 ('et',
  'permis',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [257]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [792]}},
   'weight': 2}),
 ('et',
  'messieurs',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [43]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [43]}},
   'weight': 2}),
 ('et',
  'signé',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [303]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [838]}},
   'weight': 2}),
 ('et',
  'invalidité',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [70]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [70]}},
   'weight': 2}),
 ('société_générale',
  'ainsi',
  {'paths': {'11': {'word_positions': [336]}, '15': {'word_positions': [219]}},
   'weight': 2}),
 ('lpers',
  'et',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [364]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [900]}},
   'weight': 2}),
 ('85_0',
  '0600_4',
  {'paths': {'2': {'word_positions': [187]}, '7': {'word_positions': [197]}},
   'weight': 2}),
 ('85_0',
  '75',
  {'paths': {'29': {'word_positions': [247]}, '36': {'word_positions': [468]}},
   'weight': 2}),
 ('85_0',
  '2633',
  {'paths': {'2': {'word_positions': [287]}, '7': {'word_positions': [297]}},
   'weight': 2}),
 ('85_0',
  '5267',
  {'paths': {'2': {'word_positions': [175]}, '7': {'word_positions': [185]}},
   'weight': 2}),
 ('80_5',
  '1250_393',
  {'paths': {'37': {'word_positions': [242]}, '5': {'word_positions': [242]}},
   'weight': 2}),
 ('finances',
  'publiques',
  {'paths': {'8': {'text_data': {'length': 779},
     'text_id': 8,
     'word_positions': [672, 707]}},
   'weight': 2}),
 ('393_657',
  'cotisation_ac',
  {'paths': {'37': {'word_positions': [159]}, '5': {'word_positions': [159]}},
   'weight': 2}),
 ('alloc_famil',
  'p_deplaf',
  {'paths': {'13': {'word_positions': [236]}, '32': {'word_positions': [237]}},
   'weight': 2}),
 ('alloc_famil',
  'pzdeplaf',
  {'paths': {'20': {'word_positions': [200]}, '21': {'word_positions': [196]}},
   'weight': 2}),
 ('livret_a',
  'en_euros',
  {'paths': {'9': {'word_positions': [226, 6]}}, 'weight': 2}),
 ('livret_a',
  'pri',
  {'paths': {'11': {'word_positions': [133]}, '34': {'word_positions': [130]}},
   'weight': 2}),
 ('à_l',
  'audiovisuel_public',
  {'paths': {'8': {'word_positions': [185, 29]}}, 'weight': 2}),
 ('33',
  '1',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [230]},
    '9': {'text_data': {'length': 451},
     'text_id': 9,
     'word_positions': [389]}},
   'weight': 2}),
 ('page_1',
  'designation',
  {'paths': {'29': {'word_positions': [61]}, '36': {'word_positions': [219]}},
   'weight': 2}),
 ('rang',
  '3',
  {'paths': {'8': {'text_data': {'length': 779},
     'text_id': 8,
     'word_positions': [371, 468]}},
   'weight': 2}),
 ('rang',
  '1_ou',
  {'paths': {'8': {'word_positions': [459, 356]}}, 'weight': 2}),
 ('160',
  'fonds',
  {'paths': {'13': {'text_data': {'length': 313},
     'text_id': 13,
     'word_positions': [245]},
    '32': {'text_data': {'length': 328},
     'text_id': 32,
     'word_positions': [246]}},
   'weight': 2}),
 ('accordance_with',
  'the',
  {'paths': {'0': {'word_positions': [338]}, '14': {'word_positions': [874]}},
   'weight': 2}),
 ('relative',
  'à_la',
  {'paths': {'0': {'word_positions': [361]}, '14': {'word_positions': [897]}},
   'weight': 2}),
 ('95',
  '350_00',
  {'paths': {'2': {'word_positions': [83]}, '25': {'word_positions': [83]}},
   'weight': 2}),
 ('hero_de',
  'prestatiœ',
  {'paths': {'34': {'word_positions': [126, 152]}}, 'weight': 2}),
 ('hero_de',
  'prestaîiœ',
  {'paths': {'34': {'word_positions': [158, 143]}}, 'weight': 2}),
 ('en_euros',
  'n_30003',
  {'paths': {'6': {'word_positions': [522, 641]}}, 'weight': 2}),
 ('12',
  '00',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [478, 484]}},
   'weight': 2}),
 ('050',
  '761',
  {'paths': {'13': {'text_data': {'length': 313},
     'text_id': 13,
     'word_positions': [189]},
    '32': {'text_data': {'length': 328},
     'text_id': 32,
     'word_positions': [191]}},
   'weight': 2}),
 ('sa',
  'lutations',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [183]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [183]}},
   'weight': 2}),
 ('interviennent',
  'sous',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [356]},
    '15': {'text_data': {'length': 388},
     'text_id': 15,
     'word_positions': [239]}},
   'weight': 2}),
 ('5',
  '0910912015',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [320, 335]}},
   'weight': 2}),
 ('5',
  'copie_à',
  {'paths': {'16': {'word_positions': [192]}, '4': {'word_positions': [192]}},
   'weight': 2}),
 ('5',
  '1',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [346, 349]}},
   'weight': 2}),
 ('5',
  '85_0',
  {'paths': {'29': {'word_positions': [245]}, '36': {'word_positions': [466]}},
   'weight': 2}),
 ('sujetion',
  's_s',
  {'paths': {'20': {'word_positions': [156]}, '21': {'word_positions': [155]}},
   'weight': 2}),
 ('sujetion',
  '1300',
  {'paths': {'13': {'text_data': {'length': 313},
     'text_id': 13,
     'word_positions': [170]},
    '32': {'text_data': {'length': 328},
     'text_id': 32,
     'word_positions': [171]}},
   'weight': 2}),
 ('dossier',
  'n',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [7]},
    '15': {'text_data': {'length': 388},
     'text_id': 15,
     'word_positions': [7]}},
   'weight': 2}),
 ('__',
  '__',
  {'paths': {'19': {'text_data': {'length': 385},
     'text_id': 19,
     'word_positions': [304]},
    '8': {'text_data': {'length': 779},
     'text_id': 8,
     'word_positions': [253]}},
   'weight': 2}),
 ('duly',
  'dated',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [318]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [854]}},
   'weight': 2}),
 ('octobre',
  '2012',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [31]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [31]}},
   'weight': 2}),
 ('transférés',
  'numéro',
  {'paths': {'11': {'text_data': {'length': 494},
     'text_id': 11,
     'word_positions': [115]},
    '15': {'text_data': {'length': 388},
     'text_id': 15,
     'word_positions': [119]}},
   'weight': 2}),
 ('75_12',
  '03',
  {'paths': {'11': {'word_positions': [52]}, '34': {'word_positions': [51]}},
   'weight': 2}),
 ('perte',
  'éventuelle',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [163]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [163]}},
   'weight': 2}),
 ('par',
  'personne_s',
  {'paths': {'8': {'word_positions': [463, 454]}}, 'weight': 2}),
 ('par',
  'messagerie_dans',
  {'paths': {'9': {'word_positions': [252, 30]}}, 'weight': 2}),
 ('par',
  'rapport',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [142]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [142]}},
   'weight': 2}),
 ('par',
  'exemple',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [97]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [97]}},
   'weight': 2}),
 ('gestionnaire',
  'nicole',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [24]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [24]}},
   'weight': 2}),
 ('scientifiques',
  'de',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [396]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [932]}},
   'weight': 2}),
 ('2013',
  '0',
  {'paths': {'8': {'text_data': {'length': 779},
     'text_id': 8,
     'word_positions': [408, 439]}},
   'weight': 2}),
 ('2013',
  'sur_proposition',
  {'paths': {'14': {'word_positions': [273]}, '31': {'word_positions': [84]}},
   'weight': 2}),
 ('2013',
  'période',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [112]},
    '19': {'text_data': {'length': 385},
     'text_id': 19,
     'word_positions': [128]}},
   'weight': 2}),
 ('bordeaux',
  'téléphone',
  {'paths': {'6': {'text_data': {'length': 948},
     'text_id': 6,
     'word_positions': [88]},
    '9': {'text_data': {'length': 451},
     'text_id': 9,
     'word_positions': [276]}},
   'weight': 2}),
 ('30003',
  '01430',
  {'paths': {'21': {'text_data': {'length': 282},
     'text_id': 21,
     'word_positions': [44]},
    '32': {'text_data': {'length': 328},
     'text_id': 32,
     'word_positions': [55]}},
   'weight': 2}),
 ('valide',
  'que',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [247]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [782]}},
   'weight': 2}),
 ('valable',
  'il',
  {'paths': {'22': {'text_data': {'length': 244},
     'text_id': 22,
     'word_positions': [132]},
    '26': {'text_data': {'length': 242},
     'text_id': 26,
     'word_positions': [132]}},
   'weight': 2}),
 ('http',
  'l',
  {'paths': {'16': {'text_data': {'length': 200},
     'text_id': 16,
     'word_positions': [45]},
    '4': {'text_data': {'length': 200}, 'text_id': 4, 'word_positions': [45]}},
   'weight': 2}),
 ('pzdeplaf',
  's_s',
  {'paths': {'20': {'word_positions': [201]}, '21': {'word_positions': [197]}},
   'weight': 2}),
 ('requirements',
  'à',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [348]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [884]}},
   'weight': 2}),
 ('personnel',
  'du',
  {'paths': {'0': {'text_data': {'length': 408},
     'text_id': 0,
     'word_positions': [369]},
    '14': {'text_data': {'length': 944},
     'text_id': 14,
     'word_positions': [905]}},
   'weight': 2}),
 ('personnel',
  'de_la',
  {'paths': {'0': {'word_positions': [354]}, '14': {'word_positions': [890]}},
   'weight': 2}),
 ...]

In [20]:

    

CSV_FILE = '/media/benjamin/Largo/testspdfs/csv/table_classif.csv'


    

In [22]:

    

import csv
cluster_dic ={}
print('Loading: ',CSV_FILE)
with open(CSV_FILE, 'r') as csvfile:
	clusters_table = csv.DictReader(csvfile, delimiter=',')
	for row in clusters_table:
		for key in row.keys():
			if key in cluster_dic.keys():
				cluster_dic[key].append(row[key])
			else:
				cluster_dic[key]=[row[key]]


    

    




Loading:  /media/benjamin/Largo/testspdfs/csv/table_classif.csv

In [27]:

    

del cluster_dic['']


    

In [28]:

    

cluster_dic


    

    
Out[28]:





{'0': ['copy0007',
  'copy0005',
  'copy0010',
  '/Density\\',
  '0.6666666666666666',
  '/Shared words\\',
  '3_3 1',
  '30003_01438 1',
  'fl_fl 1',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  ''],
 '1': ['contrats_de_travail',
  'contratbricaud',
  'contrat2',
  'contrat1415003',
  'contrat1',
  '/Density\\',
  '0.5',
  '/Shared words\\',
  'art_41 1',
  'i_epfl 1',
  'original_copy 1',
  'directive_sur 1',
  '34696_modification 1',
  'téléphone_4121 1',
  'epfl_ch 1',
  'les_rapports 1',
  'bâtiment_bi 1',
  'correspondent_à 1',
  '11_11 1',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  ''],
 '2': ['decembre14',
  'aout15',
  'avril14',
  'avril15',
  'decembre15',
  '/Density\\',
  '0.4',
  '/Shared words\\',
  '389_83 1',
  '7_334 1',
  '70_780 1',
  'cotisation_frais 1',
  '12_14 1',
  '0_0958 1',
  '350_00 1',
  '40_40 1',
  '307_cotisation 1',
  '407_cotisation 1',
  '757_cotisation 1',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  ''],
 '3': ['contrat2015002',
  'contrat2015',
  '/Density\\',
  '1.0',
  '/Shared words\\',
  'mw_afs 1',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  ''],
 '4': ['avisimpots2013',
  'diplomeInfirmiere',
  'compteMarie',
  'compteMarie2',
  '/Density\\',
  '0.5',
  '/Shared words\\',
  'm_e 1',
  'envoi_n 1',
  'n_30003 1',
  '3933_votre 1',
  'au_2210912015 1',
  'votre_situation 1',
  'votre_conseiller 1',
  'en_francs 1',
  'marie_lahille 1',
  'en_france 1',
  'internet_mobile 1',
  'votre_banque 1',
  'agence_thonon 1',
  '1_ou 1',
  '222_rcs 1',
  '8_page 1',
  'en_euros 1',
  'espace_client 1',
  '81_99 1',
  'en_agence 1',
  'débit_crédit 1',
  '1_euro 1',
  'x_mon 1',
  'vir_recu 1',
  'date_valeur 1',
  '50_eur 1',
  'distance_24 1'],
 '5': ['compteversevianLahille',
  'compteversevianLahille2',
  'compteversevianjointLahilleRicaud',
  '/Density\\',
  '0.6666666666666666',
  '/Shared words\\',
  'prestation_inchange 1',
  'l_agence 1',
  'prie_prions 1',
  'effectuées_sur 1',
  'agence_actuelle 1',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  ''],
 '6': ['copy0009',
  'copy0008',
  '/Density\\',
  '1.0',
  '/Shared words\\',
  '8_8 1',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  ''],
 '7': ['aout16',
  'avril16',
  '/Density\\',
  '1.0',
  '/Shared words\\',
  '607_cotisation 1',
  '75_175 1',
  '80_5 1',
  '7_680 1',
  '1250_393 1',
  '7_724 1',
  '80_0 1',
  '393_657 1',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  ''],
 '8': ['AVS',
  'carte_AVS',
  '/Density\\',
  '1.0',
  '/Shared words\\',
  'fédérale_de 1',
  'l_avs 1',
  'avs_al 1',
  'ahv_iv 1',
  'n_d 1',
  'avs_ai 1',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '',
  '']}

In [ ]: