DeepAI AI Chat
Log In Sign Up

Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems

by   Wenqiang Lei, et al.
National University of Singapore
University of Virginia
Hefei University of Technology

Recommender systems are embracing conversational technologies to obtain user preferences dynamically, and to overcome inherent limitations of their static models. A successful Conversational Recommender System (CRS) requires proper handling of interactions between conversation and recommendation. We argue that three fundamental problems need to be solved: 1) what questions to ask regarding item attributes, 2) when to recommend items, and 3) how to adapt to the users' online feedback. To the best of our knowledge, there lacks a unified framework that addresses these problems. In this work, we fill this missing interaction framework gap by proposing a new CRS framework named Estimation-Action-Reflection, or EAR, which consists of three stages to better converse with users. (1) Estimation, which builds predictive models to estimate user preference on both items and item attributes; (2) Action, which learns a dialogue policy to determine whether to ask attributes or recommend items, based on Estimation stage and conversation history; and (3) Reflection, which updates the recommender model when a user rejects the recommendations made by the Action stage. We present two conversation scenarios on binary and enumerated questions, and conduct extensive experiments on two datasets from Yelp and LastFM, for each scenario, respectively. Our experiments demonstrate significant improvements over the state-of-the-art method CRM [32], corresponding to fewer conversation turns and a higher level of recommendation hits.


page 1

page 2

page 3

page 4


Seamlessly Unifying Attributes and Items: Conversational Recommendation for Cold-Start Users

Static recommendation methods like collaborative filtering suffer from t...

Unified Conversational Recommendation Policy Learning via Graph-based Reinforcement Learning

Conversational recommender systems (CRS) enable the traditional recommen...

Bundle MCR: Towards Conversational Bundle Recommendation

Bundle recommender systems recommend sets of items (e.g., pants, shirt, ...

Soliciting User Preferences in Conversational Recommender Systems via Usage-related Questions

A key distinguishing feature of conversational recommender systems over ...

Rethinking Conversational Recommendations: Is Decision Tree All You Need?

Conversational recommender systems (CRS) dynamically obtain the user pre...

Conversational Recommendation: Theoretical Model and Complexity Analysis

Recommender systems are software applications that help users find items...

Two-level monotonic multistage recommender systems

A recommender system learns to predict the user-specific preference or i...