Interactive Conversational Search and Recommendation by Deep Reinforcement Learning
Ali Montazeralghaem
By enabling retrieval and recommender systems to dynamically obtain user preferences through conversations with users, conversational search and recommendation have become increasingly popular in recent years. This process starts with receiving a request from the user and continues with asking clarifying questions or suggesting some possible items or documents by the system. In this way, the system can get valuable feedback from users to accurately determine the users’ needs. This process repeats until the search or recommendation is successful, or the user accepts defeat.
Recently, advances in deep reinforcement learning techniques have provided new opportunities for interactive conversational search and recommendation. In this talk, I will discuss how to develop agents with deep reinforcement learning for conversational search and recommendation in order to have flexible interaction with users to satisfy them by reaching the goal of the conversation.
Ali Montazeralghaem is a Ph.D. candidate at the University of Massachusetts, Amherst, studying computer science with research interests in various areas including information retrieval, recommender systems, deep learning and reinforcement learning methods, and natural language processing.
He has published 19 papers in top-tier ACM conferences and journals such as KDD, WSDM, WWW, RecSys, SIGIR, ECIR, and IRJ, with 11 of these papers being lead-authored. His research has been supported by the National Science Foundation, Amazon, and Microsoft. In addition to his research, Ali has also served as a program committee member and journal reviewer for ten ACM conferences and journals, including SIGIR, ACL, CIKM, EMNLP, and AAAI.