FORCE: A Framework of Rule-Based Conversational Recommender System

TL;DR

FORCE is a rule-based framework designed to enable quick and easy development of conversational recommender systems, especially effective in cold-start scenarios, without relying on large annotated datasets.

Contribution

The paper introduces FORCE, a rule-based framework that simplifies building CRS bots and addresses cold-start issues, contrasting with existing deep learning approaches.

Findings

Effective in cold-start scenarios

Validated on multiple datasets and languages

Facilitates rapid CRS development

Abstract

The conversational recommender systems (CRSs) have received extensive attention in recent years. However, most of the existing works focus on various deep learning models, which are largely limited by the requirement of large-scale human-annotated datasets. Such methods are not able to deal with the cold-start scenarios in industrial products. To alleviate the problem, we propose FORCE, a Framework Of Rule-based Conversational Recommender system that helps developers to quickly build CRS bots by simple configuration. We conduct experiments on two datasets in different languages and domains to verify its effectiveness and usability.