NLP基础：NNLM模型代码示例

from keras.models import Sequential

import numpy as np
import tensorflow as tf
import re
sentences = [ "我渴了", "你真好", "他的错", "对不起" , "他走了"]

# NNLM Parameter
n_step = len(sentences[0])-1 # number of steps ['我 渴', '你 真', '他 的', '对 不', '他 走']

#分字
def seg_char(sent):
    pattern = re.compile(r'([\u4e00-\u9fa5])')
    chars = pattern.split(sent)
    chars =[w for w in chars if len(w.strip()) > 0]
    return chars

#得到每个句子前n-1个词和目标词
chars=np.array([seg_char(i)for i in sentences])
chars=chars.reshape(1,-1)
word_list=np.squeeze(chars)
#['我' '渴' '了' '你' '真' '好' '他' '的' '错' '对' '不' '起' '他' '走' '了']
word_list = list(set(word_list))
word_dict = {w: i for i, w in enumerate(word_list)}
#{'渴': 0, '错': 1, '不': 2, '好': 3, '起': 4, '他': 5, '对': 6, '你': 7, '走': 8, '我': 9, '了': 10, '的': 11, '真': 12}
number_dict = {i: w for i, w in enumerate(word_list)}
#{0: '渴', 1: '错', 2: '不', 3: '好', 4: '起', 5: '他', 6: '对', 7: '你', 8: '走', 9: '我', 10: '了', 11: '的', 12: '真'}
n_class = len(word_dict) # number of Vocabulary

#这里通过one-hot进行词向量生成
#one-hot转换
def make_batch(sentences):
    input_batch = []
    target_batch = []

    for sen in sentences:
        #将每个句子中的字转化为下标表示
        word = seg_char(sen)
        input = [word_dict[n] for n in word[:-1]]
        target = word_dict[word[-1]]
        
        #one-hot转换
        input_batch.append(np.eye(n_class)[input])
        target_batch.append(np.eye(n_class)[target])

    return input_batch, target_batch

input_batch, target_batch=make_batch(sentences)
input_batch=np.array(input_batch)
#将输入词向量进行首尾拼接
input_batch=input_batch.reshape(-1,n_step*n_class)
target_batch=np.array(target_batch)
target_batch=target_batch.reshape(-1,n_class)

from keras.layers import Dense
import keras

#建立模型，本模型暂不包含直连边
def define_model():
    model = Sequential()

    #Dense为全连接网络
    model.add(Dense(2,activation='tanh',input_shape=(n_step*n_class,))) # 输入层
    model.add(Dense(n_class, activation='softmax'))  # 输出层
    model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
    model.summary()
    return model

#训练模型
model=define_model()
model.fit(input_batch, target_batch, epochs=2000)#训练2000轮，数据少啦，一两轮没效果

#预测测试
predict=model.predict(input_batch)