计算机与现代化

• 人工智能 • 上一篇    下一篇

基于RNN句子编码器的聊天机器人

  

  1. 河海大学计算机与信息学院,江苏-南京-211100
  • 收稿日期:2017-05-22 出版日期:2018-01-23 发布日期:2018-01-24
  • 作者简介:朱晶晶(1993-),男,安徽马鞍山人,河海大学计算机与信息学院硕士研究生,研究方向:机器学习,自然语言处理;韩立新(1967-),男,江苏南京人,研究员,博士生导师,博士,研究方向:信息检索,模式识别,数据挖掘。

Chatterbots Based on RNN Sentence Auto-encoder

  1. College of Computer and Information, Hohai University, Nanjing 211100, China
  • Received:2017-05-22 Online:2018-01-23 Published:2018-01-24

摘要: 人机对话是自然语言处理领域衍生的一项现实应用场景,根据现实获取的大量短文本知识数据,构建单轮短对话式智能应答聊天机器人。本文基于传统的信息检索式聊天机器人,引入循环神经网络(RNN)深度表征交互式知识库中短文本的语义向量,重构表达式语义空间。实验表明该编码向量的方法比传统的利用TF-IDF向量的方法效果更好。

关键词: 聊天机器人, RNN句子编码器, TF-IDF

Abstract: Man-machine dialogue is a realistic application scenario which derived from the field of natural language processing. Based on the large amount of short text knowledge obtained from reality, the man-made short dialogue intelligent response chatterbot is constructed. Based on the traditional information retrieval typed chatterbot, the Recurrent Neural Network (RNN) is introduced to characterize the semantic vector of short text in the interactive knowledge base and reconstructs the expression semantic space. Experiments show that the effect of the method of using the coding vector is improved compared with the traditional method of using TF-IDF vector.

Key words: chatterbot, RNN sentence auto-encoder, TF-IDF

中图分类号: