利用BERT构建助句进行面向方面的情感分析(NAACL 2019).zip

# coding=utf-8 """BERT finetuning runner.""" from __future__ import absolute_import, division, print_function import argparse import collections import logging import os import random import numpy as np import torch import torch.nn.functional as F from torch.utils.data import DataLoader, TensorDataset from torch.utils.data.distributed import DistributedSampler from torch.utils.data.sampler import RandomSampler, SequentialSampler from tqdm import tqdm, trange import tokenization from modeling import BertConfig, BertForSequenceClassification from optimization import BERTAdam from processor import (Semeval_NLI_B_Processor, Semeval_NLI_M_Processor, Semeval_QA_B_Processor, Semeval_QA_M_Processor, Semeval_single_Processor, Sentihood_NLI_B_Processor, Sentihood_NLI_M_Processor, Sentihood_QA_B_Processor, Sentihood_QA_M_Processor, Sentihood_single_Processor) 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__) 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, label_list, max_seq_length, tokenizer): """Loads a data file into a list of `InputBatch`s.""" label_map = {} for (i, label) in enumerate(label_list): label_map[label] = i features = [] for (ex_index, example) in enumerate(tqdm(examples)): tokens_a = tokenizer.tokenize(example.text_a) tokens_b = None if example.text_b: tokens_b = tokenizer.tokenize(example.text_b) if tokens_b: # Modifies `tokens_a` and `tokens_b` in place so that the total # length is less than the specified length. # Account for [CLS], [SEP], [SEP] with "- 3" _truncate_seq_pair(tokens_a, tokens_b, max_seq_length - 3) else: # Account for [CLS] and [SEP] with "- 2" if len(tokens_a) > max_seq_length - 2: tokens_a = tokens_a[0:(max_seq_length - 2)] # The convention in BERT is: # (a) For sequence pairs: # tokens: [CLS] is this jack ##son ##ville ? [SEP] no it is not . [SEP] # type_ids: 0 0 0 0 0 0 0 0 1 1 1 1 1 1 # (b) For single sequences: # tokens: [CLS] the dog is hairy . [SEP] # type_ids: 0 0 0 0 0 0 0 # # Where "type_ids" are used to indicate whether this is the first # sequence or the second sequence. The embedding vectors for `type=0` and # `type=1` were learned during pre-training and are added to the wordpiece # embedding vector (and position vector). This is not *strictly* necessary # since the [SEP] token unambigiously separates the sequences, but it makes # it easier for the model to learn the concept of sequences. # # For classification tasks, the first vector (corresponding to [CLS]) is # used as as the "sentence vector". Note that this only makes sense because # the entire model is fine-tuned. tokens = [] segment_ids = [] tokens.append("[CLS]") segment_ids.append(0) for token in tokens_a: tokens.append(token) segment_ids.append(0) tokens.append("[SEP]") segment_ids.append(0) if tokens_b: for token in tokens_b: tokens.append(token) segment_ids.append(1) tokens.append("[SEP]") segment_ids.append(1) input_ids = tokenizer.convert_tokens_to_ids(tokens) # 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. while len(input_ids) < max_seq_length: input_ids.append(0) input_mask.append(0) segment_ids.append(0) assert len(input_ids) == max_seq_length assert len(input_mask) == max_seq_length assert len(segment_ids) == max_seq_length label_id = label_map[example.label] features.append( InputFeatures( input_ids=input_ids, input_mask=input_mask, segment_ids=segment_ids, label_id=label_id)) return features def _truncate_seq_pair(tokens_a, tokens_b, max_length): """Truncates a sequence pair in place to the maximum length.""" # This is a simple heuristic which will always truncate the longer sequence # one token at a time. This makes more sense than truncating an equal percent # of tokens from each, since if one sequence is very short then each token # that's truncated likely contains more information than a longer sequence. while True: total_length = len(tokens_a) + len(tokens_b) if total_length <= max_length: break if len(tokens_a) > len(tokens_b): tokens_a.pop() else: tokens_b.pop() def main(): parser = argparse.ArgumentParser() ## Required parameters parser.add_argument("--task_name", default=None, type=str, required=True, choices=["sentihood_single", "sentihood_NLI_M", "sentihood_QA_M", \ "sentihood_NLI_B", "sentihood_QA_B", "semeval_single", \ "semeval_NLI_M", "semeval_QA_M", "semeval_NLI_B", "semeval_QA_B"], help="The name of the task to train.") parser.add_argument("--data_dir", default=None, type=str, required=True, help="The input data dir. Should contain the .tsv files (or other data files) for the task.") parser.add_argument("--vocab_file", default=None, type=str, required=True, help="The vocabulary file that the BERT model was trained on.") parser.add_argument("--bert_config_file", default=None, type=str, required=True, help="The config json file corresponding to the pre-trained BERT model. \n" "This specifies the model architecture.") parser.add_argument("--output_dir", default=None, type=str, required=True, help="The output directory where the model checkpoints will be written.") ## Other parameters parser.add_argument("--init_checkpoint", default=None, type=str, help="Initial checkpoint (usually from a pre-trained BERT model).") parser.add_argument("--init_eval_checkpoint", default=None, type=str, help="Initial checkpoint (usually from a pre-trained BERT model + classifier).") parser.add_argument("--do_save_model", default=False, action='store_true', help="Whether to save model.") parser.add_argument("--eval_test", default=False, action='store_true', help="Whether to run eval on the test set.")