PEDNet: A Persona Enhanced Dual Alternating Learning Network for Conversational Response Generation

Proceedings of the 28th International Conference on Computational Linguistics, pages 4089–4099 Barcelona, Spain (Online), December 8-13, 2020 4089 PEDNet: A Persona Enhanced Dual Alternating Learning Network for Conversational Response Generation Bin Jiang1*, Wanyue Zhou1, Jingxu Yang1, Chao Yang1, Shihan Wang2 and Liang Pang3 1College of Computer Science and Electronic Engineering, Hunan University, China 2Intelligent Systems, Utrecht University, The Netherlands 3CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences, China {jiangbin, zhouwanyue, yangjingxv, yangchaoedu}@hnu.edu.cn s.wang2@uu.nl, pangliang@ict.ac.cn Abstract Endowing a chatbot with a personality is essential to deliver more realistic conversations. Var- ious persona-based dialogue models have been proposed to generate personalized and diverse responses by utilizing predefined persona information. However, generating personalized re- sponses is still a challenging task since the leverage of predefined persona information is often insufficient. To alleviate this problem, we propose a novel Persona Enhanced Dual Alternating Learning Network (PEDNet) aiming at producing more personalized responses in various open- domain conversation scenarios. PEDNet consists of a Context-Dominated Network (CDNet) and a Persona-Dominated Network (PDNet), which are built upon a common encoder-decoder back- bone. CDNet learns to select a proper persona as well as ensure the contextual relevance of the predicted response, while PDNet learns to enhance the utilization of persona information when generating the response by weakening the disturbance of specific content in the conversation context. CDNet and PDNet are trained alternately using a multi-task training approach to equip PEDNet with the both capabilities they have learned. Both automatic and human evaluations on a newly released dialogue dataset Persona-chat demonstrate that our method could deliver more personalized responses than baseline methods. 1 Introduction Generating human-like conversations by chatbots has been a long-term goal in artificial intelligence. End-to-end neural generative models attract much attention as potential solutions to open-domain dia- logue systems, which aim to conduct smooth and natural conversations and gain trust from users. The Sequence-to-Sequence (Seq2Seq) models (Sutskever et al., 2014; Vinyals and Le, 2015; Shang et al., 2015) have achieved success in generating semantic and syntactic responses for a given conversation context. Nevertheless, Seq2Seq tends to generate short and generic responses like “I don’t know” and “I’m fine” as they predict the response by using the maximum-likelihood estimation (MLE) objective function (Li et al., 2016a). And the generated responses are often lack of consistent personality since Seq2Seq is trained over collected conversations from different speakers (Li et al., 2016b; Zhang et al., 2018). To tackle these issues, various methods have been proposed toward diverse and consistent response generation, by endowing open-domain chatbot with a coherent persona. For example, Zhang et al. (2018) introduced persona profiles in response generation where the persona information is used to enrich re- sponses, and their experiments demonstrated improvements over those not leveraging persona informa- tion. Lian et al. (2019) further proposed a persona selection method, which focused on selecting the optimal persona to generate personalized responses efficiently. These efforts have obtained considerable attention and proven that leveraging the additional persona information can …

Content truncated to 500 words