School of
Information Technology and Electrical Engineering

Speaker: Mr Xuhui Ren
Seminar Date: Fri, 11/10/2019 - 15:00
Venue: 78-631; Data Science MM Lab
Host: Dr Hongzhi Yin

Seminar Type:  PhD Confirmation Seminar

Abstract: 

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. Appropriate recommender systems will offer users easier access to preferred resources and also help service providers understand their customers better. As such, the recommender system (RS) serves a pivotal purpose of aligning available items (e.g., products, services, etc.) with user interests. 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., inquiring 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.

In order to enable two-way human-machine communications and tackle the challenges brought by manually crafted rules, we carry out our research from the perspective of conversational recommender system and design an end-to-end trainable system to tackle the task of conversational recommendation. Currently, we have proposed a Conversational Recommender System with Adversarial Learning (CRSAL), which could address the aforementioned problems and generate human-like responses in each conversation turn. We innovatively design a fully statistical dialogue state tracker coupled with a neural policy agent to precisely capture each user's demands from limited dialogue data and generate conversational recommendation actions. We further develop an adversarial advantage 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.

Biography: 

Xuhui Ren is a PhD candidate at DKE group under supervision of Dr. Hongzhi Yin and A/Prof Helen Huang. He received his Master degree and Bachelor degree in Control Theory and Control Engineering from Dalian University of Technology and China University of Mining & Technology, respectively. His research interest includes recommender systems, dialogue systems, reinforcement learning and control theory.