Open AccessAdversarial Response Generation Against Topic Relevance
Author(s) -
Peng Zhang,
Hongrong Wang,
Zhigang Zhou,
Yu Wang
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1966/1/012041
Subject(s) - adversarial system , discriminator , relevance (law) , computer science , dialog box , generative grammar , classifier (uml) , artificial intelligence , generator (circuit theory) , conversation , natural language processing , machine learning , information retrieval , world wide web , psychology , communication , telecommunications , power (physics) , physics , quantum mechanics , detector , political science , law
In recent years, generative adversarial networks have performed well in the field of dialogue generation to improve the information diversity of dialogue responses. Often overlooked, however, is that the query and response are not relevant on the topic. In order to improve the topic relevance of chat conversation, the paper proposed a topic-relevance adversarial response generation model, TR-ARG, which is composed of generator G, discriminator D and topic classifier T. The experiment was evaluated on OpenSubtitles, an open dialog dataset, and compared with the current baseline models SEQ2SEQ and GAN-AEL. The results show that our model can effectively improve the topic relevance of generated responses.