CRSAL: Conversational recommender systems with adversarial learning
Type
ArticleKAUST Department
Computer Science ProgramComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Machine Intelligence & kNowledge Engineering Lab
Date
2020-06-13Online Publication Date
2020-06-13Print Publication Date
2020-10-13Submitted Date
2019-09-01Permanent link to this record
http://hdl.handle.net/10754/665725
Metadata
Show full item recordAbstract
Recommender systems have been attracting much attention from both academia and industry because of their ability to capture user interests and generate personalized item recommendations. As the life pace in contemporary society speeds up, traditional recommender systems are inevitably limited by their disconnected interaction styles and low adaptivity to users' evolving demands. Consequently, conversational recommender systems emerge as a prospective research area, where an intelligent dialogue agent is integrated with a recommender system. Conversational recommender systems possess the ability to accurately understand end-users' intent or request and generate human-like dialogue responses when performing recommendations. However, existing conversational recommender systems only allow the systems to ask users for more preference information, while users' further questions and concerns about the recommended items (e.g., enquiring the location of a recommended restaurant) can hardly be addressed. Though the recent task-oriented dialogue systems allow for two-way communications, they are not easy to train because of their high dependence on human guidance in terms of user intent recognition and system response generation. Hence, to enable two-way human-machine communications and tackle the challenges brought by manually crafted rules, we propose Conversational Recommender System with Adversarial Learning (CRSAL), a novel end-To-end system to tackle the task of conversational recommendation. In CRSAL, we innovatively design a fully statistical dialogue state tracker coupled with a neural policy agent to precisely capture each user's intent from limited dialogue data and generate conversational recommendation actions. We further develop an adversarial Actor-Critic reinforcement learning approach to adaptively refine the quality of generated system actions, thus ensuring coherent human-like dialogue responses. Extensive experiments on two benchmark datasets fully demonstrate the superiority of CRSAL on conversational recommendation tasks.Citation
Ren, X., Yin, H., Chen, T., Wang, H., Hung, N. Q. V., Huang, Z., & Zhang, X. (2020). CRSAL. ACM Transactions on Information Systems, 38(4), 1–40. doi:10.1145/3394592Sponsors
We would like to thank our anonymous reviewers for providing insightful review comments and suggestions.DOI
10.1145/3394592Additional Links
https://dl.acm.org/doi/10.1145/3394592ae974a485f413a2113503eed53cd6c53
10.1145/3394592