NLP采用Bert进行简单文本情感分类

参照当Bert遇上Kerashttps://spaces.ac.cn/archives/6736此示例准确率达到95.5%+
https://github.com/CyberZHG/keras-bert/blob/master/README.zh-CN.md

示例实现

# ! -*- coding:utf-8 -*-

import json
import numpy as np
import pandas as pd
from random import choice
from keras_bert import load_trained_model_from_checkpoint, Tokenizer
import codecs

maxlen = 100
config_path = 'model/bert_config.json'
checkpoint_path = 'model/bert_model.ckpt'
dict_path = 'model/vocab.txt'

token_dict = {
   }

with codecs.open(dict_path, 'r', 'utf8') as reader:
    for line in reader:
        token = line.strip()
        token_dict[token] = len(token_dict)


class OurTokenizer(Tokenizer):

    def __init__(self, token_dict):
        super(OurTokenizer, self).__init__(token_dict)

    def _tokenize(self, text):
        R = []
        for c in text:
            if c in self._token_dict:
                R.append(c)
            elif self._is_space(c):
                R.append('[unused1]')  # space类用未经训练的[unused1]表示
            else:
                R.append('[UNK]')  # 剩余的字符是[UNK]
        return R


tokenizer = OurTokenizer(token_dict)

neg = pd.read_excel('neg.xls', header=None)
pos = pd.read_excel('pos.xls', header=None)

data = []

for d in neg[0]:
    data.append((d, 0))

for d in pos[0]:
    data.append((d, 1))

# 按照9:1的比例划分训练集和验证集
random_order = list(range(len(data)))
np.random.shuffle(random_order)
train_data = [data[j] for i, j in enumerate(random_order) if i % 10 != 0]
valid_data = [data[j] for i, j in enumerate(random_order) if i % 10 == 0]


def seq_padding(X, padding=0):
    L = [len(x) for x in X]
    ML = max(L)
    return np.array([
        np.concatenate([x, [padding] * (ML - len(x))]) if len(x) < ML else x for x in X
    ])


class data_generator:

    def __init__(self, data, batch_size=32):
        self.data = data
        self.batch_size = batch_size
        self.steps = len(self.data) // self.batch_size
        if len(self.data) % self.batch_size != 0:
            self.steps += 1

    def __len__(self):
        return self.steps

    def __iter__(self):
        while True:
            idxs = list(range(len(self.data)))
            np.random.shuffle(idxs)
            X1, X2, Y = [], [], []
            for i in idxs:
                d = self.data[i]
                text = d[0][:maxlen]
                x1, x2 = tokenizer.encode(first=text)
                y = d[1]
                X1.append(x1)
                X2.append(x2)
                Y.append([y])
                if len(X1) == self.batch_size or i ==