基于场景与话题的聊天型人机会话系统  

Human-machine conversation system for chatting based on scene and topic

作　　者：陆思聪[1] 李春文[1] LU Sicong;LI Chunwen(Department of Automation,Tsinghua University,Beijing 100084,China)

机构地区：[1]清华大学自动化系,北京100084

出　　处：《清华大学学报（自然科学版）》2022年第5期952-958,共7页Journal of Tsinghua University(Science and Technology)

基　　金：国家自然科学基金面上项目(61174068)。

摘　　要：人机会话在自然语言处理乃至人工智能领域中起着重要标志性作用,可根据使用目的划分为问答系统、任务型会话、聊天系统等,其中聊天型会话通常具有更高的拟人需求。该文在基于长短期记忆网络的序列变换模型基础上,通过引入话题网络显式抽取会话中的场景与话题信息,并将这种不随语序变化的高层抽象信息扩展到会话模型结构中,与注意力机制共同指导解码预测过程。由于难以事先获取话题信息,话题网络被建模为非监督式学习模型,因此训练过程需分三步进行。实验结果表明,在恰当的训练方法和结构参数下,该模型能够使聊天会话的质量得到明显提升。Human-machine conversation plays an important role in natural language processing and artificial intelligence. Human-machine conversation can be divided into the question answering system, task-oriented conversation, and chatting system according to the purpose of use. Among them, the chatting system usually requires higher personification. Based on the sequence transformation model of the long short-term memory network, the topic network is introduced in this study to explicitly extract the scene and topic information from the conversation, and this higher-level feature, which does not change with the word order, is inputted to the structure of the conversation model to guide the decoding and prediction processes together with the attention mechanism. Because of the difficulty of obtaining the topic information in advance, the topic network is modeled as an unsupervised learning structure. Thus, the training process needs to be divided into three steps. The experimental results show that the model can significantly improve the quality of the chatting system with appropriate training methods and structural parameters.

关 键 词：人工智能 自然语言处理 人机会话 机器学习 话题网络 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]