In [1]:
EATINGMEAT_BECAUSE_TRAIN = "../data/interim/eatingmeat_because_xl_train_withprompt.ndjson"
EATINGMEAT_BECAUSE_TEST = "../data/interim/eatingmeat_because_xl_test_withprompt.ndjson"
EATINGMEAT_BUT_TRAIN = "../data/interim/eatingmeat_but_xl_train_withprompt.ndjson"
EATINGMEAT_BUT_TEST = "../data/interim/eatingmeat_but_xl_test_withprompt.ndjson"
JUNKFOOD_BECAUSE_TRAIN = "../data/interim/junkfood_because_train_withprompt.ndjson"
JUNKFOOD_BUT_TRAIN = "../data/interim/junkfood_but_train_withprompt.ndjson"
In [2]:
import ndjson
input_file = EATINGMEAT_BECAUSE_TRAIN
with open(input_file) as i:
data = ndjson.load(i)
texts = [item["text"] for item in data]
labels = [item["label"] for item in data]
In [3]:
from torch import nn
from pytorch_transformers.modeling_bert import BertPreTrainedModel, BertModel
class BertForSequenceEmbeddings(BertPreTrainedModel):
r"""
**labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size,)``:
Labels for computing the sequence classification/regression loss.
Indices should be in ``[0, ..., config.num_labels - 1]``.
If ``config.num_labels == 1`` a regression loss is computed (Mean-Square loss),
If ``config.num_labels > 1`` a classification loss is computed (Cross-Entropy).
Outputs: `Tuple` comprising various elements depending on the configuration (config) and inputs:
**loss**: (`optional`, returned when ``labels`` is provided) ``torch.FloatTensor`` of shape ``(1,)``:
Classification (or regression if config.num_labels==1) loss.
**logits**: ``torch.FloatTensor`` of shape ``(batch_size, config.num_labels)``
Classification (or regression if config.num_labels==1) scores (before SoftMax).
**hidden_states**: (`optional`, returned when ``config.output_hidden_states=True``)
list of ``torch.FloatTensor`` (one for the output of each layer + the output of the embeddings)
of shape ``(batch_size, sequence_length, hidden_size)``:
Hidden-states of the model at the output of each layer plus the initial embedding outputs.
**attentions**: (`optional`, returned when ``config.output_attentions=True``)
list of ``torch.FloatTensor`` (one for each layer) of shape ``(batch_size, num_heads, sequence_length, sequence_length)``:
Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
Examples::
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertForSequenceClassification.from_pretrained('bert-base-uncased')
input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute")).unsqueeze(0) # Batch size 1
labels = torch.tensor([1]).unsqueeze(0) # Batch size 1
outputs = model(input_ids, labels=labels)
loss, logits = outputs[:2]
"""
def __init__(self, config):
super(BertForSequenceEmbeddings, self).__init__(config)
self.num_labels = config.num_labels
self.bert = BertModel(config)
self.dropout = nn.Dropout(config.hidden_dropout_prob)
self.classifier = nn.Linear(config.hidden_size, self.config.num_labels)
self.apply(self.init_weights)
def forward(self, input_ids, token_type_ids=None, attention_mask=None, labels=None,
position_ids=None, head_mask=None):
outputs = self.bert(input_ids, position_ids=position_ids, token_type_ids=token_type_ids,
attention_mask=attention_mask, head_mask=head_mask)
pooled_output = outputs[1]
pooled_output = self.dropout(pooled_output)
return pooled_output
In [4]:
label2idx = {}
idx2label = {}
target_names = []
for item in data:
if item["label"] not in label2idx:
target_names.append(item["label"])
idx = len(label2idx)
label2idx[item["label"]] = idx
idx2label[idx] = item["label"]
print(label2idx)
print(idx2label)
{'Meat industry produces greenhouse gases and/or uses water - general': 0, 'Meat industry produces greenhouse gases and/or uses water - specific numbers': 1, 'Because as preposition': 2, 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water': 3, "Outside of article's scope": 4, 'Irrelevant fact from article': 5, 'Meat industry harms animals': 6, 'Meat industry produces greenhouse gases and/or uses water - incorrect numbers or comparison': 7}
{0: 'Meat industry produces greenhouse gases and/or uses water - general', 1: 'Meat industry produces greenhouse gases and/or uses water - specific numbers', 2: 'Because as preposition', 3: 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water', 4: "Outside of article's scope", 5: 'Irrelevant fact from article', 6: 'Meat industry harms animals', 7: 'Meat industry produces greenhouse gases and/or uses water - incorrect numbers or comparison'}
In [5]:
import torch
from pytorch_transformers.tokenization_bert import BertTokenizer
from pytorch_transformers.modeling_bert import BertForSequenceClassification
BERT_MODEL = 'bert-base-uncased'
BATCH_SIZE = 16 if "base" in BERT_MODEL else 2
tokenizer = BertTokenizer.from_pretrained(BERT_MODEL)
model = BertForSequenceEmbeddings.from_pretrained(BERT_MODEL, num_labels=len(label2idx))
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)
model.eval()
Out[5]:
BertForSequenceEmbeddings(
(bert): BertModel(
(embeddings): BertEmbeddings(
(word_embeddings): Embedding(30522, 768, padding_idx=0)
(position_embeddings): Embedding(512, 768)
(token_type_embeddings): Embedding(2, 768)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
(encoder): BertEncoder(
(layer): ModuleList(
(0): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
(1): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
(2): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
(3): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
(4): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
(5): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
(6): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
(7): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
(8): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
(9): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
(10): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
(11): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): BertLayerNorm()
(dropout): Dropout(p=0.1)
)
)
)
)
(pooler): BertPooler(
(dense): Linear(in_features=768, out_features=768, bias=True)
(activation): Tanh()
)
)
(dropout): Dropout(p=0.1)
(classifier): Linear(in_features=768, out_features=8, bias=True)
)
In [6]:
import logging
import numpy as np
logging.basicConfig(format = '%(asctime)s - %(levelname)s - %(name)s - %(message)s',
datefmt = '%m/%d/%Y %H:%M:%S',
level = logging.INFO)
logger = logging.getLogger(__name__)
MAX_SEQ_LENGTH=100
class InputFeatures(object):
"""A single set of features of data."""
def __init__(self, input_ids, input_mask, segment_ids, label_id):
self.input_ids = input_ids
self.input_mask = input_mask
self.segment_ids = segment_ids
self.label_id = label_id
def convert_examples_to_features(examples, label2idx, max_seq_length, tokenizer, verbose=0):
"""Loads a data file into a list of `InputBatch`s."""
features = []
for (ex_index, ex) in enumerate(examples):
# TODO: should deal better with sentences > max tok length
input_ids = tokenizer.encode("[CLS] " + ex["text"] + " [SEP]")
segment_ids = [0] * len(input_ids)
# The mask has 1 for real tokens and 0 for padding tokens. Only real
# tokens are attended to.
input_mask = [1] * len(input_ids)
# Zero-pad up to the sequence length.
padding = [0] * (max_seq_length - len(input_ids))
input_ids += padding
input_mask += padding
segment_ids += padding
assert len(input_ids) == max_seq_length
assert len(input_mask) == max_seq_length
assert len(segment_ids) == max_seq_length
label_id = label2idx[ex["label"]]
if verbose and ex_index == 0:
logger.info("*** Example ***")
logger.info("text: %s" % ex["text"])
logger.info("input_ids: %s" % " ".join([str(x) for x in input_ids]))
logger.info("input_mask: %s" % " ".join([str(x) for x in input_mask]))
logger.info("segment_ids: %s" % " ".join([str(x) for x in segment_ids]))
logger.info("label:" + str(ex["label"]) + " id: " + str(label_id))
features.append(
InputFeatures(input_ids=input_ids,
input_mask=input_mask,
segment_ids=segment_ids,
label_id=label_id))
return features
features = convert_examples_to_features(data, label2idx, MAX_SEQ_LENGTH, tokenizer, verbose=0)
In [7]:
import torch
from torch.utils.data import TensorDataset, DataLoader
def get_data_loader(features, max_seq_length, batch_size, shuffle=True):
all_input_ids = torch.tensor([f.input_ids for f in features], dtype=torch.long)
all_input_mask = torch.tensor([f.input_mask for f in features], dtype=torch.long)
all_segment_ids = torch.tensor([f.segment_ids for f in features], dtype=torch.long)
all_label_ids = torch.tensor([f.label_id for f in features], dtype=torch.long)
data = TensorDataset(all_input_ids, all_input_mask, all_segment_ids, all_label_ids)
dataloader = DataLoader(data, shuffle=False, batch_size=batch_size)
return dataloader
dataloader = get_data_loader(features, MAX_SEQ_LENGTH, BATCH_SIZE)
In [8]:
from tqdm import tqdm_notebook as tqdm
def get_embeddings(model, dataloader):
embeddings = []
for step, batch in enumerate(tqdm(dataloader, desc="Evaluation iteration")):
batch = tuple(t.to(device) for t in batch)
input_ids, input_mask, segment_ids, label_ids = batch
with torch.no_grad():
output = model(input_ids, segment_ids, input_mask, label_ids)
for embedding in output:
embeddings.append(embedding.cpu().numpy())
return embeddings
model.eval()
embeddings = get_embeddings(model, dataloader)
In [9]:
from sklearn.cluster import KMeans
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
from collections import Counter
NUM_CLUSTERS = 400
clusterer = KMeans(n_clusters=NUM_CLUSTERS)
clusters = clusterer.fit_predict(embeddings)
cluster_sizes = Counter(clusters)
print(clusters)
print(len(clusters))
print(cluster_sizes)
[153 156 74 ... 124 63 150]
1411
Counter({70: 29, 69: 29, 176: 25, 8: 25, 97: 24, 92: 23, 22: 23, 20: 21, 170: 21, 7: 20, 60: 20, 39: 19, 192: 19, 88: 18, 107: 18, 12: 18, 141: 18, 44: 17, 161: 17, 121: 17, 162: 17, 74: 16, 124: 16, 25: 16, 15: 15, 14: 15, 90: 14, 61: 14, 154: 14, 32: 13, 73: 13, 147: 13, 63: 13, 137: 13, 56: 12, 95: 12, 38: 12, 45: 12, 184: 12, 29: 12, 104: 11, 106: 11, 160: 11, 76: 11, 117: 11, 79: 11, 146: 11, 186: 10, 140: 10, 16: 10, 71: 10, 82: 10, 152: 10, 112: 10, 115: 10, 167: 10, 91: 10, 126: 10, 193: 9, 109: 9, 66: 9, 17: 9, 127: 9, 41: 9, 48: 9, 75: 9, 100: 9, 50: 9, 47: 8, 35: 8, 83: 8, 62: 8, 197: 8, 158: 8, 153: 7, 165: 7, 130: 7, 11: 7, 142: 7, 30: 7, 24: 7, 134: 7, 10: 7, 54: 7, 2: 6, 199: 6, 36: 6, 189: 6, 129: 6, 4: 6, 80: 6, 188: 6, 93: 5, 67: 5, 135: 5, 64: 5, 31: 5, 119: 5, 26: 5, 114: 5, 139: 5, 194: 5, 94: 5, 168: 5, 87: 5, 13: 4, 198: 4, 108: 4, 53: 4, 113: 4, 105: 4, 51: 4, 116: 4, 122: 4, 77: 4, 5: 4, 84: 4, 59: 4, 46: 4, 190: 4, 3: 4, 58: 4, 110: 4, 156: 3, 155: 3, 111: 3, 171: 3, 98: 3, 173: 3, 78: 3, 0: 3, 49: 3, 150: 3, 86: 3, 72: 3, 145: 3, 85: 3, 42: 3, 172: 3, 9: 3, 21: 3, 123: 3, 159: 3, 131: 2, 68: 2, 89: 2, 181: 2, 175: 2, 43: 2, 185: 2, 33: 2, 182: 2, 180: 2, 1: 2, 174: 2, 163: 2, 57: 2, 52: 2, 183: 2, 144: 2, 28: 2, 99: 2, 55: 1, 148: 1, 101: 1, 178: 1, 177: 1, 37: 1, 149: 1, 164: 1, 151: 1, 125: 1, 23: 1, 6: 1, 40: 1, 187: 1, 179: 1, 34: 1, 102: 1, 19: 1, 103: 1, 196: 1, 191: 1, 18: 1, 169: 1, 133: 1, 166: 1, 138: 1, 120: 1, 27: 1, 128: 1, 65: 1, 195: 1, 118: 1, 96: 1, 132: 1, 157: 1, 143: 1, 136: 1, 81: 1})
In [10]:
clusterer.cluster_centers_
Out[10]:
array([[-0.9505169 , -0.68017868, -0.95877838, ..., -0.83899872,
-0.82063476, 0.87458197],
[-0.94499856, -0.61573002, -0.87534899, ..., -0.66477925,
-0.77391395, 0.8640039 ],
[-0.9240385 , -0.644036 , -0.9545625 , ..., -0.85496757,
-0.77432412, 0.84850415],
...,
[-0.94747965, -0.65990806, -0.9212835 , ..., -0.75006493,
-0.79532123, 0.85357852],
[-0.91962829, -0.60387237, -0.95953868, ..., -0.82855639,
-0.74633121, 0.84468724],
[-0.94430504, -0.67319156, -0.90976948, ..., -0.7872068 ,
-0.80191703, 0.83319217]])
In [11]:
from collections import defaultdict
from scipy import spatial
cluster_items = defaultdict(list)
for idx, cluster in enumerate(clusters):
cluster_items[cluster].append(idx)
diverse_data = []
for cluster in range(NUM_CLUSTERS):
cluster_center = clusterer.cluster_centers_[cluster]
similarities = []
for item_idx in cluster_items[cluster]:
similarity = 1-spatial.distance.cosine(embeddings[item_idx], cluster_center)
similarities.append(similarity)
most_central_item_idx = cluster_items[cluster][similarities.index(max(similarities))]
diverse_data.append(data[most_central_item_idx])
print(diverse_data)
[{'text': 'Large amounts of meat consumption are harming the environment, because raising and transporting them causes unwanted greenhouse gases, amounting to masses larger than what cars produce.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': "Large amounts of meat consumption are harming the environment, because greenhouse gases for this industry account for 1/5 of the world's.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because it takes a lot of greenhouse production.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because of greenhouse gasses', 'label': 'Because as preposition'}, {'text': 'Large amounts of meat consumption are harming the environment, because transporting these animals makes up one fifth of the earths greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising domestic livestock is not efficient because it takes a huge amount of water and releases an enormous amount of greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because the process causes 1/5 of the earths green house gases', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because it creates greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising animals and transporting meat produces a large amount of greenhouse gasses.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because Water supplies are being depleted.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because the act of raising the animals to maturity creates one-fifth of the greenhouse gases that we make as humans.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because of the enormous amount of greenhouse gases being created from the livestock.', 'label': 'Because as preposition'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising and transporting meats produces one fifth of greenhouse gases on the earth.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising meat consumes large amounts of water.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising and transporting animals emits a substantial amount of greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': "Large amounts of meat consumption are harming the environment, because One fifth of the Earth's greenhouse gases are produced from raising animals and transporting meat.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': "Large amounts of meat consumption are harming the environment, because it produces 1/5 of the earth's greenhouse gases to raise and transport meat.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because the resources needed to transport and maintain the production are very harmful to the environment.', 'label': 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water'}, {'text': "Large amounts of meat consumption are harming the environment, because raising animals for meet uses almost half the water in the U.S. and makes one fifth of the earth's greenhouse gases.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': "Large amounts of meat consumption are harming the environment, because it's not good for you.", 'label': "Outside of article's scope"}, {'text': 'Large amounts of meat consumption are harming the environment, because raising livestock is responsible for almost one-fifth of the greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because of the space to free range animals', 'label': 'Because as preposition'}, {'text': "Large amounts of meat consumption are harming the environment, because Raising animals and transporting meat creates almost a fifth of the earth's greenhouse gases.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because vast resources we no longer have are being spent on raising livestock.', 'label': 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water'}, {'text': 'Large amounts of meat consumption are harming the environment, because the production of meat creates large amount of greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because animals and transporting meat creates almost one-fifth of the earth’s greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because it is taking animals from the environment with are a part of nature.', 'label': 'Meat industry harms animals'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising meet requires a lot of water and mya also disturb the ecosytem', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because it can effect the population rate of the animals that we are eating, and could affect the food chain.', 'label': 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising animals and transporting them produce high amounts of greenhouse gases', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because , of raising animals and transporting meat.', 'label': 'Because as preposition'}, {'text': 'Large amounts of meat consumption are harming the environment, because of how natural resources (water, fuel) are used to raise the animals and transport the food.', 'label': 'Because as preposition'}, {'text': 'Large amounts of meat consumption are harming the environment, because it creates more greenhouse gases', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': "Large amounts of meat consumption are harming the environment, because they are responsible for almost one-fifth of the earth's greenhouse gases and almost half of the water used in the U.S.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because the raising and transporting of meat is a large contributor of green house gases', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because of the greenhouse gases.', 'label': 'Because as preposition'}, {'text': 'Large amounts of meat consumption are harming the environment, because it is creating 20% of all the greenhouse gases on Earth.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because the lesser those animals are, the more risk of having inbalance in the environment', 'label': 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water'}, {'text': 'Large amounts of meat consumption are harming the environment, because the raising of livestock creates a lot of greenhouse gas.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because it is contributing to greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because it has a huge impact on our nature', 'label': 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water'}, {'text': 'Large amounts of meat consumption are harming the environment, because the cost of raising and transporting animals creates a large amount of greenhouse gases that harm the earth.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because they attribute to one-fifth of all of the greenhouse gases on earth.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising beef harms the environment in so many ways: the waste produced by the animals is killing the soil and polluting our air, methane gas given off by cattle alone is causing serious harm to the air, and finally, the amount of energy used to produce a pound of meat is wasteful', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': "Large amounts of meat consumption are harming the environment, because it creates one fifth of the world's greenhouse gases.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising and selling meat creates a lot of harmful gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because the means to produce it is detrimental to the environment', 'label': 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water'}, {'text': 'Large amounts of meat consumption are harming the environment, because of the greenhouse gases resulting from raising and transporting the livestock.', 'label': 'Because as preposition'}, {'text': "Large amounts of meat consumption are harming the environment, because they create 1/5 of the Earth's greenhouse gasses.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because global warming Moderation is the key to healthy balance', 'label': 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising and moving meat creates large amounts of greenhouse gases on the Earth.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because the animals have too much gas!', 'label': 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water'}, {'text': 'Large amounts of meat consumption are harming the environment, because it takes a lot of land to raise that amount of animals to support the demand.', 'label': 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water'}, {'text': 'Large amounts of meat consumption are harming the environment, because it uses half of our water and produces a great deal of Greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because of the amount of green house gas that is produce in 9 rider to transport the meat across region', 'label': 'Because as preposition'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising animals and transporting them creates greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because it takes away our animals.', 'label': 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water'}, {'text': 'Large amounts of meat consumption are harming the environment, because it creates much greenhouse gas', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because they are creating a lot of greenhouse gases and hurt the Earth.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising and transporting meat causes one fifth of greenhouse gas emissions.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because producing and shipping meat products create a huge amount of greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because it generates a lot of greenhouse gas.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising animals and transportation of meat creates a lot of greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': "Large amounts of meat consumption are harming the environment, because raising livestock and transporting meat is responsible for creating one fifth of the earth's greenhouse gas emission which is harming earth and also consumes almost half of the water used in the U.S.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': "Large amounts of meat consumption are harming the environment, because it contributes to 1/5 of the word's greenhouse gasses.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': "Large amounts of meat consumption are harming the environment, because of raising and transporting meat creates almost 1/5th of the Earth's greenhouse gases.", 'label': 'Because as preposition'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising livestock uses half the water in the US and contributes to 1/5 of greenhouse gases globally.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because it uses a lot of water', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': "Large amounts of meat consumption are harming the environment, because raising and transporting meat creates one-fifth of the earth's greenhouse gases.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because they increase greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because it contributes to 1/5 of the total greenhouse gases produced on earth.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': "Large amounts of meat consumption are harming the environment, because one fifth of earth's greenhouse gases.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because the meat industry creates one-fifth of greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': "Large amounts of meat consumption are harming the environment, because it creates one fifth of the earth's greenhouse gases.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because it creates more greenhouse gases than those created by cars, trucks, trains, and airplanes combined.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because it increases the production of green house gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because transporting meat causes a lot of greenhouse gases', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because because the raising of the animal contributes to green house gases and over utilizes our water supply.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': "Large amounts of meat consumption are harming the environment, because they cause one fifth of the earth's greenhouse gases.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising the animals creates even more greenhouse gas emissions into the atmosphere.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising and transporting livestock creates large amounts of greenhouse gases, lol.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because one fifth of greenhouse gases come from animals and 50% of the water used in the USA is for raising animals.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising livestock and exporting meats causes more greenhouse gases than all motor vehicles, planes, and trains combined.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': "Large amounts of meat consumption are harming the environment, because the raising of animals behind the meat, cause almost one-fifth of the earth's greenhouse gases.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because of all the pollution that goes with it from the air pollution to the use of water needed for raising animals', 'label': 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water'}, {'text': 'Large amounts of meat consumption are harming the environment, because transporting meat alone creates one fifth of the greenhouse gases on our planet.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because they create green house gasses', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising animals and transporting meat contributes to greenhouse gases in the atmosphere.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because it used a lot of greenhouse gases and a lot of water.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': "Large amounts of meat consumption are harming the environment, because raising and transporting animals cause 1/5 of the world's greenhouse gases and raising livestock consumes almost half of all water used in the US.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because it creates a lot of greenhouse gas to produce and ship the meat.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because it raises levels of greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because they increase the amount of green house gas through there transportation and irrigation cost.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because it creates greenhouse gases at a tremendous rate, and uses way too much water for the livestock.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because Raising animals and transporting them creates one fifth of the earths greenhouse gasses.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': "Large amounts of meat consumption are harming the environment, because it's easy to find it", 'label': "Outside of article's scope"}, {'text': 'Large amounts of meat consumption are harming the environment, because raising animals creates greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because it takes a lot of water to provide the animals with all of the food and water they need.', 'label': 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising animals and transporting meats is the cause of 1/5 of green house gasses', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because the amount of greenhouse gases is so high.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because they take large amount of natural resources to take care of a raise, From the land they feed of of to the water that hydrate them', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because the raising of livestock using half of the water resources in the U.S.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': "Large amounts of meat consumption are harming the environment, because it2 of creates 1/5 of the world's air pollution and uses 1/2 of our water.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because processing meat is using resources and creating green house gasses.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because it takes a lot of resources to support it.', 'label': 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water'}, {'text': 'Large amounts of meat consumption are harming the environment, because of large amounts of greenhouse gas created in production.', 'label': 'Because as preposition'}, {'text': 'Large amounts of meat consumption are harming the environment, because there are chemicals created from raising animals.', 'label': 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water'}, {'text': 'Large amounts of meat consumption are harming the environment, because they create greenhouse gasses and use a lot of water.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because half of water used in the US goes to raising livestock.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising and transporting them is creating a staggering amount of greenhouse gases and using a lot of our drinking water.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': "Large amounts of meat consumption are harming the environment, because it's creating 1/5th of earth's greenhouse gases.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because it creates 1/5 of the earths greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because it can eliminate one fifth on the greenhouse gas', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because the meat industry generates a fifth of greenhouse gases and accounts for half of American water use.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because of its greenhouse gases being created and water usage from raising livestock.', 'label': 'Because as preposition'}, {'text': "Large amounts of meat consumption are harming the environment, because the transportation of meat contributes to about one fifth of the earth's greenhouse gases, which is larger than the fraction of greenhouse gases that cars, trucks, trains and airplanes produce combined.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': "Large amounts of meat consumption are harming the environment, because it causes one-fifth of the earth's greenhouse gases.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because rasing livestock uses almost half the water avalible in the US', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because the transportation of meat products causes significant amounts of greenhouse gases and water usage.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because one fifth of greenhouse gases are emitted transporting neat.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because it requires a lot of natural resources to produce and transport.', 'label': 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water'}, {'text': 'Large amounts of meat consumption are harming the environment, because a majority of our water goes to taking care of the animals.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because the transportation contributes to 1/5 of green house gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because of the large amount of greenhouse gases created.', 'label': 'Because as preposition'}, {'text': 'Large amounts of meat consumption are harming the environment, because according to this source-free paragraph it creates nearly 1/5 of all supposedly harmful greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because the meat industry produces a huge amount of greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because over half of the water used in the United States goes to raising animals for slaughter and one fifth of the earths green house gasses are created by raised animals.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because its wrong.', 'label': "Outside of article's scope"}, {'text': 'Large amounts of meat consumption are harming the environment, because of the green house gasses.', 'label': 'Because as preposition'}, {'text': 'Large amounts of meat consumption are harming the environment, because the cause one fifth of the greenhouse gases to get them from farm to fork.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising cattle requires a lot of water and outputs a lot of green house gases', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because its not what we are supposed to be eating all the time our bodies dont really know how to digest it and all the live stock is making more greenhouse gases then cars and machines put together', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because they are creating greenhouse gasses that combined are more that what transportation, such as cars, , trucks, plains combined cause.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because 1/2 of the water in the US goes towards feeding livestock.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because it generates 1/5 of the earths green house gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because Transportings animals hurt green house gas', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': "Large amounts of meat consumption are harming the environment, because raising animals and transporting meat produces almost one-fifth of the earth's greenhouse gases.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because not everyond should eat meat its not good for everyone not everyone can digest it', 'label': "Outside of article's scope"}, {'text': "Large amounts of meat consumption are harming the environment, because they are a major source of earth's greenhouse gases", 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising and transportation creates almost one-fifth of greenhouse gases', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because of greenhouse gases associated with raising meat.', 'label': 'Because as preposition'}, {'text': 'Large amounts of meat consumption are harming the environment, because the energy it takes to transport meat produces a lot of greenhouse gases and uses up a lot of water.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because a group of animal lovers think so.', 'label': "Outside of article's scope"}, {'text': 'Large amounts of meat consumption are harming the environment, because raising animals and transporting the meat comprises about one-fifth of all greeenhouse gasses.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because transportation for those meats causes 1/5 of the greenhouse gasses harming the earth right now.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because the process raising and consuming meat create a large amount of greenhouse gasses and also use up our water supply.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because of greenhouse gases', 'label': 'Because as preposition'}, {'text': 'Large amounts of meat consumption are harming the environment, because it pollutes our country.', 'label': 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water'}, {'text': 'Large amounts of meat consumption are harming the environment, because the raising and transport of meat creates a lot of "greenhouse gases"', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because it puts a stress on water supplies and can cause large amounts of greenhouse gasses.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because animals are grown in cafos not small farme where poop becomes veggies', 'label': "Outside of article's scope"}, {'text': 'Large amounts of meat consumption are harming the environment, because producing meat causes greenhouse gases and uses up water resources.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because almost half of the water used goes to raising livestock.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': "Large amounts of meat consumption are harming the environment, because they create one-fifth of the earth's greenhouse gasses.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because production creates 1/5 of the greenhouse gases and requires 1/2 of the water used in the U.S.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because it takes more than just eating it to cause problems, transportation and methane can be harmful', 'label': 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water'}, {'text': 'Large amounts of meat consumption are harming the environment, because it causes overcomsumption which can drive the market to generate more product which thus leads to more environmental usage', 'label': 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water'}, {'text': "Large amounts of meat consumption are harming the environment, because raising livestock uses up a lot of Earth's natural resources, and exporting the meat in vehicles contributes to the greenhouse gases.", 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because rasing animals and transporting them creates about one fifth of the earths greenhouse gases', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising livestockcreates greenhouse gases and uses a lot of water.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': "Large amounts of meat consumption are harming the environment, because raising animals and transporting the meat creates almost 1/5 of earth's greenhouse gases.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising animals and transporting meat creates greenhouse gasses.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because eliminating meat would be like giving up an essential part of our culture and traditions.', 'label': 'Irrelevant fact from article'}, {'text': 'Large amounts of meat consumption are harming the environment, because the massive amount of farm animals are polluting the planet', 'label': 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water'}, {'text': 'Large amounts of meat consumption are harming the environment, because Greenhouse gases from transporting the meat', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because it creates about 1/5 of the earths green house gases', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because of the greenhouse gas production and massive water consumption to generate meat.', 'label': 'Because as preposition'}, {'text': 'Large amounts of meat consumption are harming the environment, because of water consumption.', 'label': 'Because as preposition'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising animals transporting meat contributes almost 20% to the production of greenhouse gases, according to the article.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because transporting meat creates almost 1/5 of greenhouse gas.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because half of the water we have goes to raising livestock', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising and transporting the livestock create one-fifth of the earths green house gas emissions', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': "Large amounts of meat consumption are harming the environment, because raising animals for food accounts for almost one-fifth of the earth's greenhouse gas emissions and uses almost half of the water used in the U.S.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because we are killing animals.', 'label': "Outside of article's scope"}, {'text': 'Large amounts of meat consumption are harming the environment, because raising animals and transporting thee meat creates 1/5 of the earth greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising and transporting animals creates one fifth of greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because environmental protection', 'label': 'Irrelevant fact from article'}, {'text': 'Large amounts of meat consumption are harming the environment, because the amount of bacteria found in meat can be very harmful to the body', 'label': "Outside of article's scope"}, {'text': 'Large amounts of meat consumption are harming the environment, because the green house gasses generated from livestock production makes up one fifth of the total earths emissions', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising the animals uses up resources like water and transporting the animals to various places contributes to air pollution in the form of greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because according to the report just raising the animals creates one-fifth of greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because we are producing too many greenhouse gases and almost half of the water consumption goes to raising animals for consumption.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because the process creates a lot of greenhouse gases and uses half the water in America.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because of the greenhouse gases that are created to raise livestock.', 'label': 'Because as preposition'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising livestock creates a great deal of greenhouse gases and consumes a lot of our clean water.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because the raising of the animals and transportation of the meats is creating 1/5 of the greenhouse gases on earth.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because of the vehicles required to move them', 'label': 'Because as preposition'}, {'text': 'Large amounts of meat consumption are harming the environment, because it is not good for the environment.', 'label': 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water'}, {'text': 'Large amounts of meat consumption are harming the environment, because it takes up resources that would otherwise be beneficial for us to sustain and not waste.', 'label': 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water'}, {'text': 'Large amounts of meat consumption are harming the environment, because transporting them across the country is creating many greenhouse gases.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because land is used to raise animals instead of crops, precious water and soil are lost, trees are cut down to make land for grazing or factory-farm sheds, and untreated animal waste pollutes rivers and streams', 'label': 'Meat industry harms environment/uses resources w/o mentioning greenhouse gases or water'}, {'text': 'Large amounts of meat consumption are harming the environment, because it produces greenhouse gas.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because it contributes to greenhouse gasses', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because of the large amount of greenhosue gases that the transportation of animals is emitting.', 'label': 'Because as preposition'}, {'text': "Large amounts of meat consumption are harming the environment, because raising livestock and transporting them from the farm to your table creates almost one-fifth of the entire world's greenhouse gasses.", 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because green house gases', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising animals produce 1/5 of the greenhouse gases', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising the livestock requires alot of water.', 'label': 'Meat industry produces greenhouse gases and/or uses water - general'}, {'text': 'Large amounts of meat consumption are harming the environment, because raising animals and transporting meat contributes to about 1/5 of the greenhouse gases being spewed into the atmosphere.', 'label': 'Meat industry produces greenhouse gases and/or uses water - specific numbers'}]
In [12]:
output_file = input_file.replace("withprompt", f"withprompt_diverse{NUM_CLUSTERS}")
with open(output_file, "w") as o:
ndjson.dump(diverse_data, o)
In [ ]:
In [ ]:
Content source: empirical-org/WikipediaSentences
Similar notebooks: