Knowledge Enhanced Multi-Domain Recommendations in an AI Assistant Application

TL;DR

This paper presents a unified model that combines multi-domain user interaction data and external knowledge graphs to enhance recommendation accuracy in a conversational AI assistant across multiple content domains.

Contribution

It introduces a novel approach that integrates multi-domain interactions with knowledge graph information, demonstrating additive benefits over existing methods.

Findings

Significant improvement in overall recommendation quality.

Enhanced recommendations for new users in a domain.

Effective integration of multi-domain data and knowledge graphs.

Abstract

This work explores unifying knowledge enhanced recommendation with multi-domain recommendation systems in a conversational AI assistant application. Multi-domain recommendation leverages users' interactions in previous domains to improve recommendations in a new one. Knowledge graph enhancement seeks to use external knowledge graphs to improve recommendations within a single domain. Both research threads incorporate related information to improve the recommendation task. We propose to unify these approaches: using information from interactions in other domains as well as external knowledge graphs to make predictions in a new domain that would not be possible with either information source alone. We develop a new model and demonstrate the additive benefit of these approaches on a dataset derived from millions of users' queries for content across three domains (videos, music, and books) in a live virtual assistant application. We demonstrate significant improvement on overall recommendations as well as on recommendations for new users of a domain.