BERT+TextCNN实现医疗意图识别项目

BERT+TextCNN实现医疗意图识别项目

一、说明

本项目采用医疗意图识别数据集CMID传送门
数据集示例：

{"originalText":"间质性肺炎的症状?","entities":[{"label_type":"疾病和诊断","start_pos":0,"end_pos":5}],"seg_result":["间质性肺炎","的","症状","?"],"label_4class":["病症"],"label_36class":["临床表现"]}

模型使用BERT、TextCNN实现意图分类

二、BERT模型加载

使用苏建林开发的bert4keras深度学习框架加载BERT模型

from bert4keras.backend import keras,set_gelu
from bert4keras.models import build_transformer_model # 加载BERT的方法from bert4keras.optimizers import Adam # 优化器
set_gelu('tanh')

1.定义函数加载BERT

defbuild_bert_model(config_path , checkpoint_path , class_nums):# config_path配置文件的路径 checkpoint_path预训练路径 class_nums类别的数量
    bert = build_transformer_model(
        config_path = config_path ,
        checkpoint_path = checkpoint_path ,
        model ='bert',
        return_keras_model=False)# 在BERT模型输出中抽取[CLS]
    cls_features = keras.layers.Lambda(lambda x:x[:,0],name='cls-token')(bert.model.output)# [:,0]选取输出的第一列，BERT模型的输出中[CLS]在第一个位置 shape = [batch_size ,768]
    all_token_embedding = keras.layers.Lambda(lambda x:x[:,1:-1],name='all-token')(bert.model.output)# 获取第2列至倒数第二列的所有token  shape = [batch_size ,maxlen-2,768] 除去CLS、SEP# textcnn抽取特征
    cnn_features = textcnn(all_token_embedding, bert.initializer)# 输入all_token_embedding  shape = [batch_size,cnn_output_dim]# 将cls_features 与 cnn_features 进行拼接
    concat_features = keras.layers.concatenate([cls_features,cnn_features],axis=-1)# 全连接层
    dense = keras.layers.Dense (
        units=512,# 输出维度
        activation ='relu',# 激活函数
        kernel_initializer= bert.initializer # bert权重初始化)(concat_features)# 输入# 输出
    output = keras.layers.Dense (
        units= class_nums,# 输出类别数量
        activation='softmax',# 激活函数 (多分类输出层最常用的激活函数)
        kernel_initializer= bert.initializer # bert权重初始化)(dense)# 输入
    model = keras.models.Model(bert.model.input,output)# (bert.model.input输入，output输出)print(model.summary())return model

2.实现TextCNN

deftextcnn(input,kernel_initializer):# 3,4,5
    cnn1 = keras.layers.Conv1D(256,# 卷积核数量3,# 卷积核大小
        strides=1,# 步长
        padding='same',# 输出与输入维度一致
        activation='relu',# 激活函数
        kernel_initializer = kernel_initializer # 初始化器)(input)# shape = [batch_size ,maxlen-2,256]
    cnn1 = keras.layers.GlobalAvgPool1D()(cnn1)# 全局最大池化操作 shape = [batch_size ,256]
    cnn2 = keras.layers.Conv1D(256,# 卷积核数量4,# 卷积核大小
        strides=1,# 步长
        padding='same',# 输出与输入维度一致
        activation='relu',# 激活函数
        kernel_initializer=kernel_initializer  # 初始化器)(input)
    cnn2 = keras.layers.GlobalAvgPool1D()(cnn2)# 全局最大池化操作 shape = [batch_size ,256]
    cnn3 = keras.layers.Conv1D(256,# 卷积核数量5,# 卷积核大小
        strides=1,# 步长
        padding='same',# 输出与输入维度一致
        kernel_initializer=kernel_initializer  # 初始化器)(input)
    cnn3 = keras.layers.GlobalAvgPool1D()(cnn3)# 全局最大池化操作 shape = [batch_size ,256]# 将三个卷积结果进行拼接
    output = keras.layers.concatenate([cnn1,cnn2,cnn3],
                                   axis=-1)
    output = keras.layers.Dropout(0.2)(output)# 最后接Dropoutreturn output

3.程序入口

if __name__ =='__main__':
    config_path ='.\chinese_L-12_H-768_A-12\\bert_config.json'
    checkpoint_path ='.\chinese_L-12_H-768_A-12\\bert_model.ckpt'
    class_nums =13
    build_bert_model(config_path , checkpoint_path , class_nums)

其中BERT模型文件可以自行在Github中下载，也可私信。

当程序开始加载模型时，表示运行成功。
切记！运行代码前，检查TensorFlow、bert4keras等第三方库的版本是否一致，否则容易报错！
4.本项目第三方库以及对应的版本

pyahocorasick==1.4.2
requests==2.25.1
gevent==1.4.0
jieba==0.42.1
six==1.15.0
gensim==3.8.3
matplotlib==3.1.3
Flask==1.1.1
numpy==1.16.0
bert4keras==0.9.1
tensorflow==1.14.0
Keras==2.3.1
py2neo==2020.1.1
tqdm==4.42.1
pandas==1.0.1
termcolor==1.1.0
itchat==1.3.10
ahocorasick==0.9
flask_compress==1.9.0
flask_cors==3.0.10
flask_json==0.3.4
GPUtil==1.4.0
pyzmq==22.0.3
scikit_learn==0.24.1

三、数据预处理

抽取CMID.json中的数据，并划分为训练集与测试集
从中选取13个类别作为最终意图分类的标签

定义
病因
预防
临床表现(病症表现)
相关病症
治疗方法
所属科室
传染性
治愈率
禁忌
化验/体检方案
治疗时间
其他

1.抽取数据

defgen_training_data(row_data_path):
    label_list =[line.strip()for line inopen('./dataset/label','r',encoding='utf8')]print(label_list)# 映射id，为每一条数据添加id
    label2id ={label : idx for idx, label inenumerate(label_list)}
    data =[]withopen('./dataset/CMID.json','r',encoding='utf8')as f :
        origin_data = f.read()
        origin_data =eval(origin_data)
    label_set =set()for item in origin_data :
        text = item['originalText']
        label_class = item['label_4class'][0].strip("'")if label_class =='其他':
            data.append([text , label_class ,label2id[label_class]])continue
        label_class = item["label_36class"][0].strip("'")# 所有的意图标签都从label_36class中取出
        label_set.add(label_class)if label_class notin label_list:continue
        data.append([text, label_class ,label2id[label_class]])print(label_set)
    data = pd.DataFrame(data , columns=['text','label_class','label'])print(data['label_class'].value_counts())
    data['text_len']= data['text'].map(lambda x :len(x))# 序列长度print(data['text_len'].describe())
    plt.hist(data['text_len'], bins=30, rwidth=0.9, density=True)
    plt.show()del data['text_len']
    data = data.sample(frac =1.0)# 将数据集拆分为测试集和训练集
    train_num =int(0.9*len(data))
    train , test = data[:train_num],data[train_num:]
    train.to_csv('./dataset/train.csv', index=False)
    test.to_csv('./dataset/test.csv', index =False)

2.加载训练数据集

# 加载训练数据集defload_data(filename):
    df = pd.read_csv(filename , header=0)return df[['text','label']].values

3.数据集信息可视化

数据样本长度基本上在100以内，此时在BERT模型中可以设置样本最大长度为128.
4.划分的训练集与测试集示例
训练集

测试集

四、模型训练

1.定义配置文件以及超参数

# 定义超参数和配置文件
class_nums =13
maxlen =128
batch_size =32
config_path ='./chinese_rbt3_L-3_H-768_A-12/bert_config_rbt3.json'
checkpoint_path ='./chinese_rbt3_L-3_H-768_A-12/bert_model.ckpt'
dict_path ='./chinese_rbt3_L-3_H-768_A-12/vocab.txt'
tokenizer = Tokenizer(dict_path)

2.定义数据生成器，将样本传递到模型中

# 定义数据生成器 将数据传递到模型中classdata_generator(DataGenerator):"""
    数据生成器
    """def__iter__(self , random =False):
        batch_token_ids , batch_segment_ids , batch_labels =[],[],[]# 对于每一个batchsize的训练，包括 token  分隔符segment 标签label三者的序列for is_end,(text , label )in self.sample(random):
            token_ids , segments_ids = tokenizer.encode(text , maxlen=maxlen)# [1,3,2,5,9,12,243,0,0,0]  编码token和分隔符segment序列，按照最大长度进行padding
            batch_token_ids.append(token_ids)
            batch_segment_ids.append(segments_ids)
            batch_labels.append([label])iflen(batch_token_ids)== self.batch_size or is_end :
                batch_token_ids = sequence_padding(batch_token_ids)
                batch_segment_ids =sequence_padding(batch_segment_ids)
                batch_labels = sequence_padding(batch_labels)yield[batch_token_ids , batch_segment_ids],batch_labels
                batch_token_ids,batch_segment_ids,batch_labels =[],[],[]

3.程序入口

if __name__ =='__main__':# 加载数据集
    train_data = load_data('./dataset/train.csv')
    test_data = load_data('./dataset/test.csv')# 转换数据集
    train_generator = data_generator(train_data,batch_size)
    test_generator = data_generator(test_data,batch_size)
    model = build_bert_model(config_path, checkpoint_path ,class_nums)print(model.summary())
    model.compile(
        loss='sparse_categorical_crossentropy',# 离散值损失函数 交叉熵损失
        optimizer=Adam(5e-6),
        metrics=['accuracy'])
    earlystop = keras.callbacks.EarlyStopping(
        monitor='var_loss',
        patience=3,
        verbose=2,
        mode='min')
    bast_model_filepath ='./chinese_L-12_H-768_A-12/best_model.weights'
    checkpoint = keras.callbacks.ModelCheckpoint(
        bast_model_filepath ,
        monitor ='val_loss',
        verbose=1,
        save_best_only=True,
        mode='min')
    model.fit_generator(
        train_generator.forfit(),
        steps_per_epoch=len(train_generator),
        epochs=10,
        validation_data=test_generator.forfit(),
        validation_steps=len(test_generator),
        shuffle=True,
        callbacks=[earlystop,checkpoint])
    model.load_weights(bast_model_filepath)
    test_pred =[]
    test_true =[]for x, y in test_generator:
        p = model.predict(x).argmax(axis=1)
        test_pred.extend(p)
    test_true = test_data[:1].tolist()print(set(test_true))print(set(test_pred))
    target_names =[line.strip()for line inopen('label','r',encoding='utf8')]print(classification_report(test_true , test_pred ,target_names=target_names))

五、运行