Task06-基于深度学习的文本分类04

基于Bert的文本分类

Bert Pretrain

预训练过程使用了Google基于Tensorflow发布的BERT源代码。首先从原始文本中创建训练数据，由于本次比赛的数据都是ID，这里重新建立了词表，并且建立了基于空格的分词器。

class WhitespaceTokenizer(object):
    """WhitespaceTokenizer with vocab."""
    def __init__(self, vocab_file):
        self.vocab = load_vocab(vocab_file)
        self.inv_vocab = {
   v: k for k, v in self.vocab.items()}

    def tokenize(self, text):
        split_tokens = whitespace_tokenize(text)
        output_tokens = []
        for token in split_tokens:
            if token in self.vocab:
                output_tokens.append(token)
            else:
                output_tokens.append("[UNK]")
        return output_tokens

    def convert_tokens_to_ids(self, tokens):
        return convert_by_vocab(self.vocab, tokens)

    def convert_ids_to_tokens(self, ids):
        return convert_by_vocab(self.inv_vocab, ids)

预训练由于去除了NSP预训练任务，因此将文档处理多个最大长度为256的段，如果最后一个段的长度小于256/2则丢弃。每一个段执行按照BERT原文中执行掩码语言模型，然后处理成tfrecord格式。

def create_segments_from_document(document, max_segment_length):
    """Split single document to segments according to max_segment_length."""
    assert len(document) == 1
    document = document[0]
    document_len = len(document)

    index = list(range(0, document_len, max_segment_length))
    other_len = document_len % max_segment_length
    if other_len > max_segment_length / 2:
        index.append(document_len)

    segments = []
    for i in range(len(index) - 1):
        segment = document[index[i]: index[i+1]]
        segments.append(segment)

    return segments

在预训练过程中，也只执行掩码语言模型任务，因此不再计算下一句预测任务的loss。

(masked_lm_loss, masked_lm_example_loss, masked_lm_log_probs) = get_masked_lm_output(
    bert_config, model.get_sequence_output(), model.get_embedding_table(),
    masked_lm_positions, masked_lm_ids, masked_lm_weights)

total_loss = masked_lm_loss

为了适配句子的长度，以及减小模型的训练时间，我们采取了BERT-mini模型，详细配置如下。

{
   
  "hidden_size": 256,
  "hidden_act": "gelu",
  "initializer_range": 0.02,
  "vocab_size": 5981,
  "hidden_dropout_prob": 0.1,
  "num_attention_heads": 4,
  "type_vocab_size": 2,
  "max_position_embeddings": 256,
  "num_hidden_layers": 4,
  "intermediate_size": 1024,
  "attention_probs_dropout_prob": 0.1
}

由于我们的整体框架使用Pytorch，因此需要将最后一个检查点转换成Pytorch的权重。

def convert_tf_checkpoint_to_pytorch(tf_checkpoint_path, bert_config_file, pytorch_dump_path):
    # Initialise PyTorch model
    config = BertConfig.from_json_file(bert_config_file)
    print("Building PyTorch model from configuration: {}".format(str(config)))
    model = BertForPreTraining(config)

    # Load weights from tf checkpoint
    load_tf_weights_in_bert(model, config, tf_checkpoint_path)

    # Save pytorch-model
    print("Save PyTorch model to {}".format(pytorch_dump_path))
    torch.save(model.state_dict(), pytorch_dump_path)

预训练消耗的资源较大，硬件条件不允许的情况下建议直接下载开源的模型

微调将最后一层的第一个token即[CLS]的隐藏向量作为句子的表示，然后输入到softmax层进行分类。

sequence_output, pooled_output = \
    self.bert(input_ids=input_ids, token_type_ids=token_type_ids)

if self.pooled:
    reps = pooled_output
else:
    reps = sequence_output[:, 0, :]  # sen_num x 256

if self.training:
    reps = self.dropout(reps)

本章小结

本章介绍了Bert的原理和使用，具体包括pretrain和finetune两部分。

本章作业

• 完成Bert Pretrain和Finetune的过程
• 阅读Bert官方文档，找到相关参数进行调参

import logging
import random
import pandas as pd
import numpy as np
import torch

logging.basicConfig(level=logging.INFO, format='%(asctime)-15s %(levelname)s: %(message)s')

# set seed
seed = 666
random.seed(seed)
np.random.seed(seed)
torch.cuda.manual_seed(seed)
torch.manual_seed(seed)

# 设置GPU
gpu = 0
use_cuda = gpu >= 0 and torch.cuda.is_available()
if use_cuda:
    torch.cuda.set_device(gpu)
    device = torch.device("cuda", gpu)
else:
    device = torch.device("cpu")
logging.info("Use cuda: %s, gpu id: %d.", use_cuda, gpu)

2020-08-05 03:14:10,414 INFO: Use cuda: True, gpu id: 0.

# 十折交叉验证
fold_num = 10
data_file = 'data/train_set.csv'

def all_data2fold(fold_num, num=10000):
    fold_data = []
    f = pd.read_csv(data_file, sep='\t', encoding='UTF-8')
    texts = f['text'].tolist()[:num]
    labels = f['label'].tolist()[:num]

    total = len(labels)

    index = list(range(total))
    np.random.shuffle(index)

    all_texts = []
    all_labels = []
    for i in index:
        all_texts.append(texts[i])
        all_labels.append(labels[i])

    label2id = {
   }
    for i in range(total):
        label = str(all_labels[i])
        if label not in label2id:
            label2id[label] = [i]
        else:
            label2id[label].append(i)

    all_index = [[] for _ in range(fold_num)]
    for label, data in label2id.items():
        # print(label, len(data))
        batch_size = int(len(data) / fold_num)
        other = len(data) - batch_size * fold_num
        for i in range(fold_num):
            cur_batch_size = batch_size + 1 if i < other else batch_size
            # print(cur_batch_size)
            batch_data = [data[i * batch_size + b] for b in range(cur_batch_size)]
            all_index[i].extend(batch_data)

    batch_size = int(total / fold_num)
    other_texts = []
    other_labels = []
    other_num = 0
    start = 0
    for fold in range(fold_num):
        num = len(all_index[fold])
        texts = [all_texts[i] for i in all_index[fold]]
        labels = [all_labels[i] for i in all_index[fold]]

        if num > batch_size:
            fold_texts = texts[:batch_size]
            other_texts.extend(texts[batch_size:])
            fold_labels = labels[:batch_size]
            other_labels.extend(labels[batch_size:])
            other_num += num - batch_size
        elif num < batch_size:
            end = start + batch_size - num
            fold_texts = texts + other_texts[start: end]
            fold_labels = labels + other_labels[start: end]
            start = end
        else:
            fold_texts = texts
            fold_labels = labels

        assert batch_size == len(fold_labels)

        # 打乱顺序
        index = list(range(batch_size))
        np.random.shuffle(index)

        shuffle_fold_texts = []
        shuffle_fold_labels = []
        for i in index:
            shuffle_fold_texts.append(fold_texts[i])
            shuffle_fold_labels.append(fold_labels[i])

        data = {
   'label': shuffle_fold_labels, 'text': shuffle_fold_texts}
        fold_data.append(data)

    logging.info("Fold lens %s", str([len(data['label']) for data in fold_data]))

    return fold_data


fold_data = all_data2fold(10)
# 训练集、验证集和测试集
fold_id = 9
# 验证集
dev_data = fold_data[fold_id]

# 训练集
train_texts = []
train_labels = []
for i in range(0, fold_id):
    data = fold_data[i]
    train_texts.extend(data['text'])
    train_labels.extend(data[</