Work

Rethinking Conversational Recommendations

Year: 2022

Type: conference-paper

Abstract: Conversational recommender systems (CRS) dynamically obtain the users' preferences via multi-turn questions and answers. The existing CRS solutions are widely dominated by deep reinforcement learning algorithms. However, deep reinforcement learning methods are often criticized for lacking interpretability and requiring a large amount of training data to perform.

Source: Proceedings of the ... ACM International Conference on Information & Knowledge Management

DOI: 10.1145/3511808.3557433

Authors: A S M Ahsan-Ul Haque, Hongning Wang

Institution: University of Virginia

Language: English

Topic: Recommender Systems and Techniques

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: National Science Foundation

Awards: CAREER: Human-Centric Knowledge Discovery and Decision Optimization, III: Small: Towards Explainable Personalization, III: Small: Moving offline learning to rank online, from theory to practice