基于深度学习的多方对话研究综述  

A survey of multi-party dialogue research based on deep learning

作　　者：张开颜 张伟男[1] 刘挺[1] Kaiyan ZHANG;Wei-Nan ZHANG;Ting LIU(Research Center for Social Computing and Information Retrieval,Harbin Institute of Technology,Harbin 150001,China)

机构地区：[1]哈尔滨工业大学社会计算与信息检索研究中心,哈尔滨150001

出　　处：《中国科学：信息科学》2021年第8期1217-1232,共16页Scientia Sinica(Informationis)

摘　　要：近年来,随着深度学习技术的广泛应用,人机对话研究取得了突破性进展.但是,目前的人机对话系统大多是在人机双方参与的假设下进行设计的,而更具挑战性的人机多方对话的研究和应用尚不成熟.本文将立足于自然语言处理领域,对近几年基于深度学习的多方对话研究进展进行综述.首先从人机对话角度出发,整理多方对话系统的关键问题和已有解决方案;然后,梳理基于多方对话的其他自然语言处理任务;之后,总结已有多方对话研究的数据集,并分析现有数据集的局限性和改进方案;最后,展望多方对话研究的未来发展趋势.In recent years, with the extensive application of deep learning technology, breakthroughs have been made in the study of human-computer dialogue. However, most of the current human-machine dialogue systems are designed under the assumption that both parties are involved, and the research and application of more challenging multi-party human-machine dialogues are not yet mature. Based on the field of natural language processing, this paper will review the research progress of multi-party dialogue based on deep learning in recent years. First, from the perspective of human-machine dialogue, we sort out the key problems and existing solutions of the multi-party dialogue system;then, we introduce other natural language processing tasks based on multi-party dialogue;afterwards, we summarize the existing multi-party dialogue research dataset and make a comparative analysis of limitations on the existing dataset;Finally, we look forward to the future development trend of multi-party dialogue research.

关 键 词：自然语言处理 深度学习 人机对话 多方对话 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]