Context-Controlled Topic-Aware Neural Response Generation for Open-Domain Dialog Systems. Issue 1 (January 2021)

• Record Type: Journal Article
• Authors: Ling, Yanxiang; Cai, Fei; Hu, Xuejun; Liu, Jun; Chen, Wanyu; Chen, Honghui
• Is Part Of: Information processing & management. Volume 58:Issue 1(2021)
• Publication Date: 2021-01
• Subjects: Response Generation -- Topic-aware -- Context -- Open-domain Dialog System; Information storage and retrieval systems -- Periodicals; Information science -- Periodicals; Systèmes d'information -- Périodiques; Sciences de l'information -- Périodiques; Information science; Information storage and retrieval systems; Periodicals; 658.4038
• DOI: 10.1016/j.ipm.2020.102392
• Languages: English
• ISSNs: 0306-4573

Abstract

Abstract: Incorporating topic information can help response generation models to produce informative responses for chat-bots. Previous work only considers the individual semantic of each topic, ignoring its specific dialog context, which may result in inaccurate topic representation and hurt response coherence. Besides, as an important feature of multi-turn conversation, dynamic topic transitions have not been well-studied. We propose a C ontext-C ontrolled T opic-A ware neural response generation model, i.e., CCTA, which makes dialog context interact with the process of topic representing and transiting to achieve balanced improvements on response informativeness and contextual coherence. CCTA focuses on capturing the semantical relations within topics as well as their corresponding contextual information in conversation, to produce context-dependent topic representations at the word-level and turn-level. Besides, CCTA introduces a context-controlled topic transition strategy, utilizing contextual topics to yield relevant transition words. Extensive experimental results on two benchmark multi-turn conversation datasets validate the superiority of our proposal on generating coherent and informative responses against the state-of-the-art baselines. We also find that topic transition modeling can work as an auxiliary learning task to boost the response generation.