摘要
现有的对话系统中存在着生成“好的”“我不知道”等无意义的安全回复问题。日常对话中,对话者通常围绕特定的主题进行讨论且每句话都有明显的情感和意图。因此该文提出了基于对话约束的回复生成模型,即在Seq2Seq模型的基础上,结合对对话的主题、情感、意图的识别。该方法对生成回复的主题、情感和意图进行约束,从而生成具有合理的情感和意图且与对话主题相关的回复。实验证明,该文提出的方法能有效提高生成回复的质量。
Existing dialogue systems tend to generate meaningless general replies such as“OK”and“I don’t know”.In daily dialogs,every utterance usually has obvious emotional and intentional tendencies.So this paper proposes a response generation model based on dialogue constraints.Based on the Seq2 Seq model,it combines the recognition of utterances’themes,sentiments and intentions.This method constrains the topics,emotions and intentions of the generated responses,generating responses with reasonable sentiment and intention tendencies and close relation to the topic of the conversation.Experiments show that the method proposed in this paper can effectively improve the quality of generated responses.
作者
管梦雨
王中卿
李寿山
周国栋
GUAN Mengyu;WANG Zhongqing;LI Shoushan;ZHOU Guodong(School of Computer Science and Technology,Soochow University,Suzhou,Jiangsu 215006,China)
出处
《中文信息学报》
CSCD
北大核心
2022年第8期144-153,共10页
Journal of Chinese Information Processing
基金
国家自然科学基金青年基金(61806137)。
关键词
对话生成
主题识别
情感识别
意图识别
dialogue generation
topic recognition
sentiment recognition
act recognition
