【Chatbot】2：中文聊天机器人的实现
前言：
上一篇【聊天机器人】1：DeepQA使用自己的数据集做chatbot上传后，收到了好多伙伴支持，在这里表示感谢。上一篇也遗留了一个问题——介于DeepQA是一个以英文语料为场景的聊天机器人，在中文场景应用中得到的结果却不尽人意。于是经过多方查找及资料整理，今天给大家分享一个以自己制作的语料集作为背景数据集的中文聊天机器人，源码也是无偿奉上供大家参考，感谢大家支持。
–-----------------------------------------------------------------------------—--------------------------------------------
–-----------------------------------------------------------------------------—--------------------------------------------
本文源码下载——请下载，文末也有源码
特别注意：本博文用的数据集很少，使用时候一定要拓展数据集
–-----------------------------------------------------------------------------—--------------------------------------------
–-----------------------------------------------------------------------------—--------------------------------------------
一、伪代码解析
1.1、模型构造
聊天机器人大多都是采用seq2seq结构，更细化的说可以指RNN网络或者LSTM网络。模型构造这个函数就是利用TensorFlow框架定义网络模型的结构，如果你对RNN网络或者LSTM网络不是很了解，我这里有一篇自己写的入门级的讲解——【深度学习】6：RNN递归神经网络原理、与MNIST数据集实现数字识别，就可以知道下面RNN网络是怎样识别一句话，其中的cell是怎样的工作原理了。
def get_model(feed_previous=False):
"""
构造模型
"""
learning_rate = tf.Variable(float(init_learning_rate), trainable=False, dtype=tf.float32)
learning_rate_decay_op = learning_rate.assign(learning_rate * 0.9)
encoder_inputs = []
decoder_inputs = []
target_weights = []
for i in range(input_seq_len):
encoder_inputs.append(tf.placeholder(tf.int32, shape=[None], name="encoder{0}".format(i)))
for i in range(output_seq_len + 1):
decoder_inputs.append(tf.placeholder(tf.int32, shape=[None], name="decoder{0}".format(i)))
for i in range(output_seq_len):
target_weights.append(tf.placeholder(tf.float32, shape=[None], name="weight{0}".format(i)))
# decoder_inputs左移一个时序作为targets
targets = [decoder_inputs[i + 1] for i in range(output_seq_len)]
cell = tf.contrib.rnn.BasicLSTMCell(size)
# 这里输出的状态我们不需要
outputs, _ = seq2seq.embedding_attention_seq2seq(
encoder_inputs,
decoder_inputs[:output_seq_len],
cell,
num_encoder_symbols=num_encoder_symbols,
num_decoder_symbols=num_decoder_symbols,
embedding_size=size,
output_projection=None,
feed_previous=feed_previous,
dtype=tf.float32)
# 计算加权交叉熵损失
loss = seq2seq.sequence_loss(outputs, targets, target_weights)
# 梯度下降优化器
opt = tf.train.GradientDescentOptimizer(learning_rate)
# 优化目标：让loss最小化
update = opt.apply_gradients(opt.compute_gradients(loss))
# 模型持久化
saver = tf.train.Saver(tf.global_variables())
return encoder_inputs, decoder_inputs, target_weights, outputs, loss, update, saver, learning_rate_decay_op, learning_rate
1.2、训练数据集加载
先看一下我自己做的问答集，question中的每一个问题依次对应answer中的一个答案，两个文件组成一个问答对构成训练集，
注意：question与answer的行数必须相同，不然会报错，且不能出现空行；
注意：数据集一定要根据需要进行扩充；
下面的代码就是通过path地址，读取两个数据集中的数据，做一定的必要处理（必要处理在下——第三个小标题），合并到一个train_set中返回：
def get_train_set():
"""
得到训练问答集
"""
global num_encoder_symbols, num_decoder_symbols
train_set = []
with open('./samples/question', 'r', encoding='utf-8') as question_file:
with open('./samples/answer', 'r', encoding='utf-8') as answer_file:
while True:
question = question_file.readline()
answer = answer_file.readline()
if question and answer:
# strip()方法用于移除字符串头尾的字符
question = question.strip()
answer = answer.strip()
# 得到分词ID
question_id_list = get_id_list_from(question)
answer_id_list = get_id_list_from(answer)
if len(question_id_list) > 0 and len(answer_id_list) > 0:
answer_id_list.append(EOS_ID)
train_set.append([question_id_list, answer_id_list])
else:
break
return train_set
1.3、必要处理——构造样本数据
如果我们将所有的数据不加处理直接放入同一个train_set中返回，程序是无法区别哪些是问题哪些是答案、问题的长度读取到哪答案的长度读取到哪——我们需要给问题和答案做一些小标记：
①、我们事先定义好输入、输出的长度，这样读取的长度、输出的长度就固定下来了，程序只需每次通过固定长度就可以取出想要的数据；
②、对于输入长度超标的数据，我们只能选择截断原有的输入——不过我们可以增大输入序列长度啊，这样不就不会被截断了
③、对于长度不够输出序列长度的输出，我们采用末尾添0，保证所有的输入、输出长度都相同；
GO_ID = 1 # 输出序列起始标记
EOS_ID = 2 # 结尾标记
PAD_ID = 0 # 空值填充0
batch_num = 1000 # 参与训练的问答对个数
input_seq_len = 25 # 输入序列长度
output_seq_len = 50 # 输出序列长度
上面就是定义输入、输出序列长度，以及起始标记、结束填充，下面就是构造样本数据函数代码
def get_samples(train_set, batch_num):
"""
构造样本数据:传入的train_set是处理好的问答集
batch_num:让train_set训练集里多少问答对参与训练
# train_set = [[[5, 7, 9], [11, 13, 15, EOS_ID]], [[7, 9, 11], [13, 15, 17, EOS_ID]], [[15, 17, 19], [21, 23, 25, EOS_ID]]]
"""
raw_encoder_input = []
raw_decoder_input = []
if batch_num >= len(train_set):
batch_train_set = train_set
else:
random_start = random.randint(0, len(train_set)-batch_num)
batch_train_set = train_set[random_start:random_start+batch_num]
# 添加起始标记、结束填充
for sample in batch_train_set:
raw_encoder_input.append([PAD_ID] * (input_seq_len - len(sample[0])) + sample[0])
raw_decoder_input.append([GO_ID] + sample[1] + [PAD_ID] * (output_seq_len - len(sample[1]) - 1))
encoder_inputs = []
decoder_inputs = []
target_weights = []
for length_idx in range(input_seq_len):
encoder_inputs.append(np.array([encoder_input[length_idx] for encoder_input in raw_encoder_input], dtype=np.int32))
for length_idx in range(output_seq_len):
decoder_inputs.append(np.array([decoder_input[length_idx] for decoder_input in raw_decoder_input], dtype=np.int32))
target_weights.append(np.array([
0.0 if length_idx == output_seq_len - 1 or decoder_input[length_idx] == PAD_ID else 1.0 for decoder_input in raw_decoder_input
], dtype=np.float32))
return encoder_inputs, decoder_inputs, target_weights
1.4、训练过程
训练过程就是激活TensorFlow框架，往模型中feed数据，并得到训练的loss，最后是保存参数
def train():
"""
训练过程
"""
train_set = get_train_set()
with tf.Session() as sess:
encoder_inputs, decoder_inputs, target_weights, outputs, loss, update, saver, learning_rate_decay_op, learning_rate = get_model()
sess.run(tf.global_variables_initializer())
# 训练很多次迭代，每隔100次打印一次loss，可以看情况直接ctrl+c停止
previous_losses = []
for step in range(epochs):
sample_encoder_inputs, sample_decoder_inputs, sample_target_weights = get_samples(train_set, batch_num)
input_feed = {}
for l in range(input_seq_len):
input_feed[encoder_inputs[l].name] = sample_encoder_inputs[l]
for l in range(output_seq_len):
input_feed[decoder_inputs[l].name] = sample_decoder_inputs[l]
input_feed[target_weights[l].name] = sample_target_weights[l]
input_feed[decoder_inputs[output_seq_len].name] = np.zeros([len(sample_decoder_inputs[0])], dtype=np.int32)
[loss_ret, _] = sess.run([loss, update], input_feed)
if step % 100 == 0:
print('step=', step, 'loss=', loss_ret, 'learning_rate=', learning_rate.eval())
#print('333', previous_losses[-5:])
if len(previous_losses) > 5 and loss_ret > max(previous_losses[-5:]):
sess.run(learning_rate_decay_op)
previous_losses.append(loss_ret)
# 模型参数保存
saver.save(sess, './model/'+ str(epochs)+ '/demo_')
#saver.save(sess, './model/' + str(epochs) + '/demo_' + step)
1.5、预测过程
预测过程就是读取model文件夹下的参数文件进行预测
def predict():
"""
预测过程
"""
with tf.Session() as sess:
encoder_inputs, decoder_inputs, target_weights, outputs, loss, update, saver, learning_rate_decay_op, learning_rate = get_model(feed_previous=True)
saver.restore(sess, './model/'+str(epochs)+'/demo_')
sys.stdout.write("you ask>> ")
sys.stdout.flush()
input_seq = sys.stdin.readline()
while input_seq:
input_seq = input_seq.strip()
input_id_list = get_id_list_from(input_seq)
if (len(input_id_list)):
sample_encoder_inputs, sample_decoder_inputs, sample_target_weights = seq_to_encoder(' '.join([str(v) for v in input_id_list]))
input_feed = {}
for l in range(input_seq_len):
input_feed[encoder_inputs[l].name] = sample_encoder_inputs[l]
for l in range(output_seq_len):
input_feed[decoder_inputs[l].name] = sample_decoder_inputs[l]
input_feed[target_weights[l].name] = sample_target_weights[l]
input_feed[decoder_inputs[output_seq_len].name] = np.zeros([2], dtype=np.int32)
# 预测输出
outputs_seq = sess.run(outputs, input_feed)
# 因为输出数据每一个是num_decoder_symbols维的，因此找到数值最大的那个就是预测的id，就是这里的argmax函数的功能
outputs_seq = [int(np.argmax(logit[0], axis=0)) for logit in outputs_seq]
# 如果是结尾符，那么后面的语句就不输出了
if EOS_ID in outputs_seq:
outputs_seq = outputs_seq[:outputs_seq.index(EOS_ID)]
outputs_seq = [wordToken.id2word(v) for v in outputs_seq]
print("chatbot>>", " ".join(outputs_seq))
else:
print("WARN：词汇不在服务区")
sys.stdout.write("you ask>>")
sys.stdout.flush()
input_seq = sys.stdin.readline()
–-----------------------------------------------------------------------------—--------------------------------------------
–-----------------------------------------------------------------------------—--------------------------------------------
二、源码说明
2.1、模型训练
点击demo_test.py文件，依次点击：run、Edit Configuration，出现如下窗口：
在以上Parameters中填入以下内容train，确定后再运行demo_test.py文件；
train
在面板中得到如下训练信息：
训练结束后，可以在model文件夹下看到生成的模型参数，如下所示：
到这里，训练就结束了。
2.2、模型测试
点击demo_test.py文件，依次点击：run、Edit Configuration，出现如下窗口：
将以上Parameters中填入的内容train换成任意一个字符，点击OK后再运行demo_test.py文件，进入如下人机交互式：
–-----------------------------------------------------------------------------—--------------------------------------------
–-----------------------------------------------------------------------------—--------------------------------------------
三、源码展示
3.1、demo_test.py文件
# -*- coding：utf-8 -*-
# -*- author：zzZ_CMing CSDN address:https://blog.csdn.net/zzZ_CMing
# -*- 2018/07/31；14:23
# -*- python3.5
import sys
import numpy as np
import tensorflow as tf
from tensorflow.contrib.legacy_seq2seq.python.ops import seq2seq
import word_token
import jieba
import random
size = 8 # LSTM神经元size
GO_ID = 1 # 输出序列起始标记
EOS_ID = 2 # 结尾标记
PAD_ID = 0 # 空值填充0
min_freq = 1 # 样本频率超过这个值才会存入词表
epochs = 2000 # 训练次数
batch_num = 1000 # 参与训练的问答对个数
input_seq_len = 25 # 输入序列长度
output_seq_len = 50 # 输出序列长度
init_learning_rate = 0.5 # 初始学习率
wordToken = word_token.WordToken()
# 放在全局的位置，为了动态算出 num_encoder_symbols 和 num_decoder_symbols
max_token_id = wordToken.load_file_list(['./samples/question', './samples/answer'], min_freq)
num_encoder_symbols = max_token_id + 5
num_decoder_symbols = max_token_id + 5
def get_id_list_from(sentence):
"""
得到分词后的ID
"""
sentence_id_list = []
seg_list = jieba.cut(sentence)
for str in seg_list:
id = wordToken.word2id(str)
if id:
sentence_id_list.append(wordToken.word2id(str))
return sentence_id_list
def get_train_set():
"""
得到训练问答集
"""
global num_encoder_symbols, num_decoder_symbols
train_set = []
with open('./samples/question', 'r', encoding='utf-8') as question_file:
with open('./samples/answer', 'r', encoding='utf-8') as answer_file:
while True:
question = question_file.readline()
answer = answer_file.readline()
if question and answer:
# strip()方法用于移除字符串头尾的字符
question = question.strip()
answer = answer.strip()
# 得到分词ID
question_id_list = get_id_list_from(question)
answer_id_list = get_id_list_from(answer)
if len(question_id_list) > 0 and len(answer_id_list) > 0:
answer_id_list.append(EOS_ID)
train_set.append([question_id_list, answer_id_list])
else:
break
return train_set
def get_samples(train_set, batch_num):
"""
构造样本数据:传入的train_set是处理好的问答集
batch_num:让train_set训练集里多少问答对参与训练
"""
raw_encoder_input = []
raw_decoder_input = []
if batch_num >= len(train_set):
batch_train_set = train_set
else:
random_start = random.randint(0, len(train_set)-batch_num)
batch_train_set = train_set[random_start:random_start+batch_num]
# 添加起始标记、结束填充
for sample in batch_train_set:
raw_encoder_input.append([PAD_ID] * (input_seq_len - len(sample[0])) + sample[0])
raw_decoder_input.append([GO_ID] + sample[1] + [PAD_ID] * (output_seq_len - len(sample[1]) - 1))
encoder_inputs = []
decoder_inputs = []
target_weights = []
for length_idx in range(input_seq_len):
encoder_inputs.append(np.array([encoder_input[length_idx] for encoder_input in raw_encoder_input], dtype=np.int32))
for length_idx in range(output_seq_len):
decoder_inputs.append(np.array([decoder_input[length_idx] for decoder_input in raw_decoder_input], dtype=np.int32))
target_weights.append(np.array([
0.0 if length_idx == output_seq_len - 1 or decoder_input[length_idx] == PAD_ID else 1.0 for decoder_input in raw_decoder_input
], dtype=np.float32))
return encoder_inputs, decoder_inputs, target_weights
def seq_to_encoder(input_seq):
"""
从输入空格分隔的数字id串，转成预测用的encoder、decoder、target_weight等
"""
input_seq_array = [int(v) for v in input_seq.split()]
encoder_input = [PAD_ID] * (input_seq_len - len(input_seq_array)) + input_seq_array
decoder_input = [GO_ID] + [PAD_ID] * (output_seq_len - 1)
encoder_inputs = [np.array([v], dtype=np.int32) for v in encoder_input]
decoder_inputs = [np.array([v], dtype=np.int32) for v in decoder_input]
target_weights = [np.array([1.0], dtype=np.float32)] * output_seq_len
return encoder_inputs, decoder_inputs, target_weights
def get_model(feed_previous=False):
"""
构造模型
"""
learning_rate = tf.Variable(float(init_learning_rate), trainable=False, dtype=tf.float32)
learning_rate_decay_op = learning_rate.assign(learning_rate * 0.9)
encoder_inputs = []
decoder_inputs = []
target_weights = []
for i in range(input_seq_len):
encoder_inputs.append(tf.placeholder(tf.int32, shape=[None], name="encoder{0}".format(i)))
for i in range(output_seq_len + 1):
decoder_inputs.append(tf.placeholder(tf.int32, shape=[None], name="decoder{0}".format(i)))
for i in range(output_seq_len):
target_weights.append(tf.placeholder(tf.float32, shape=[None], name="weight{0}".format(i)))
# decoder_inputs左移一个时序作为targets
targets = [decoder_inputs[i + 1] for i in range(output_seq_len)]
cell = tf.contrib.rnn.BasicLSTMCell(size)
# 这里输出的状态我们不需要
outputs, _ = seq2seq.embedding_attention_seq2seq(
encoder_inputs,
decoder_inputs[:output_seq_len],
cell,
num_encoder_symbols=num_encoder_symbols,
num_decoder_symbols=num_decoder_symbols,
embedding_size=size,
output_projection=None,
feed_previous=feed_previous,
dtype=tf.float32)
# 计算加权交叉熵损失
loss = seq2seq.sequence_loss(outputs, targets, target_weights)
# 梯度下降优化器
opt = tf.train.GradientDescentOptimizer(learning_rate)
# 优化目标：让loss最小化
update = opt.apply_gradients(opt.compute_gradients(loss))
# 模型持久化
saver = tf.train.Saver(tf.global_variables())
return encoder_inputs, decoder_inputs, target_weights, outputs, loss, update, saver, learning_rate_decay_op, learning_rate
def train():
"""
训练过程
"""
train_set = get_train_set()
with tf.Session() as sess:
encoder_inputs, decoder_inputs, target_weights, outputs, loss, update, saver, learning_rate_decay_op, learning_rate = get_model()
sess.run(tf.global_variables_initializer())
# 训练很多次迭代，每隔100次打印一次loss，可以看情况直接ctrl+c停止
previous_losses = []
for step in range(epochs):
sample_encoder_inputs, sample_decoder_inputs, sample_target_weights = get_samples(train_set, batch_num)
input_feed = {}
for l in range(input_seq_len):
input_feed[encoder_inputs[l].name] = sample_encoder_inputs[l]
for l in range(output_seq_len):
input_feed[decoder_inputs[l].name] = sample_decoder_inputs[l]
input_feed[target_weights[l].name] = sample_target_weights[l]
input_feed[decoder_inputs[output_seq_len].name] = np.zeros([len(sample_decoder_inputs[0])], dtype=np.int32)
[loss_ret, _] = sess.run([loss, update], input_feed)
if step % 100 == 0:
print('step=', step, 'loss=', loss_ret, 'learning_rate=', learning_rate.eval())
#print('333', previous_losses[-5:])
if len(previous_losses) > 5 and loss_ret > max(previous_losses[-5:]):
sess.run(learning_rate_decay_op)
previous_losses.append(loss_ret)
# 模型参数保存
saver.save(sess, './model/'+ str(epochs)+ '/demo_')
#saver.save(sess, './model/' + str(epochs) + '/demo_' + step)
def predict():
"""
预测过程
"""
with tf.Session() as sess:
encoder_inputs, decoder_inputs, target_weights, outputs, loss, update, saver, learning_rate_decay_op, learning_rate = get_model(feed_previous=True)
saver.restore(sess, './model/'+str(epochs)+'/demo_')
sys.stdout.write("you ask>> ")
sys.stdout.flush()
input_seq = sys.stdin.readline()
while input_seq:
input_seq = input_seq.strip()
input_id_list = get_id_list_from(input_seq)
if (len(input_id_list)):
sample_encoder_inputs, sample_decoder_inputs, sample_target_weights = seq_to_encoder(' '.join([str(v) for v in input_id_list]))
input_feed = {}
for l in range(input_seq_len):
input_feed[encoder_inputs[l].name] = sample_encoder_inputs[l]
for l in range(output_seq_len):
input_feed[decoder_inputs[l].name] = sample_decoder_inputs[l]
input_feed[target_weights[l].name] = sample_target_weights[l]
input_feed[decoder_inputs[output_seq_len].name] = np.zeros([2], dtype=np.int32)
# 预测输出
outputs_seq = sess.run(outputs, input_feed)
# 因为输出数据每一个是num_decoder_symbols维的，因此找到数值最大的那个就是预测的id，就是这里的argmax函数的功能
outputs_seq = [int(np.argmax(logit[0], axis=0)) for logit in outputs_seq]
# 如果是结尾符，那么后面的语句就不输出了
if EOS_ID in outputs_seq:
outputs_seq = outputs_seq[:outputs_seq.index(EOS_ID)]
outputs_seq = [wordToken.id2word(v) for v in outputs_seq]
print("chatbot>>", " ".join(outputs_seq))
else:
print("WARN：词汇不在服务区")
sys.stdout.write("you ask>>")
sys.stdout.flush()
input_seq = sys.stdin.readline()
if __name__ == "__main__":
if sys.argv[1] == 'train':
train()
else:
predict()
3.2、word_token.py文件
# -*- coding：utf-8 -*-
# -*- author：zzZ_CMing CSDN address:https://blog.csdn.net/zzZ_CMing
# -*- 2018/07/31；14:23
# -*- python3.5
import sys
import jieba
class WordToken(object):
def __init__(self):
# 最小起始id号, 保留的用于表示特殊标记
self.START_ID = 4
self.word2id_dict = {}
self.id2word_dict = {}
def load_file_list(self, file_list, min_freq):
"""
加载样本文件列表，全部切词后统计词频，按词频由高到低排序后顺次编号
并存到self.word2id_dict和self.id2word_dict中
file_list = [question, answer]
min_freq: 最小词频，超过最小词频的词才会存入词表
"""
words_count = {}
for file in file_list:
with open(file, 'r', encoding='utf-8') as file_object:
for line in file_object.readlines():
line = line.strip()
seg_list = jieba.cut(line)
for str in seg_list:
if str in words_count:
words_count[str] = words_count[str] + 1
else:
words_count[str] = 1
sorted_list = [[v[1], v[0]] for v in words_count.items()]
sorted_list.sort(reverse=True)
for index, item in enumerate(sorted_list):
word = item[1]
if item[0] < min_freq:
break
self.word2id_dict[word] = self.START_ID + index
self.id2word_dict[self.START_ID + index] = word
return index
def word2id(self, word):
# 判断word是不是字符串
if not isinstance(word, str):
print("Exception: error word not unicode")
sys.exit(1)
if word in self.word2id_dict:
return self.word2id_dict[word]
else:
return None
def id2word(self, id):
id = int(id)
if id in self.id2word_dict:
return self.id2word_dict[id]
else:
return None
–-----------------------------------------------------------------------------—--------------------------------------------
–-----------------------------------------------------------------------------—--------------------------------------------
源码链接
本文源码下载——请下载
还有一篇我的聊天机器人实现——【聊天机器人】1：DeepQA使用自己的数据集做chatbot
–-----------------------------------------------------------------------------—--------------------------------------------
–-----------------------------------------------------------------------------—--------------------------------------------