Suggest me a movie for tonight: Leveraging Knowledge Graphs for Conversational Recommendation

Abstract

Conversational recommender systems focus on the task of suggesting products to users based on the conversation flow. Recently, the use of external knowledge in the form of knowledge graphs has shown to improve the performance in recommendation and dialogue systems. Information from knowledge graphs aids in enriching those systems by providing additional information such as closely related products and textual descriptions of the items. However, knowledge graphs are incomplete since they do not contain all factual information present on the web. Furthermore, when working on a specific domain, knowledge graphs in its entirety contribute towards extraneous information and noise. In this work, we study several subgraph construction methods and compare their performance across the recommendation task. We incorporate pre-trained embeddings from the subgraphs along with positional embeddings in our models. Extensive experiments show that our method has a relative improvement of at least 5.62% compared to the state-of-the-art on multiple metrics on the recommendation task.

A Comprehensive Survey of Knowledge Graph-Based Recommender Systems: Technologies, Development, and Contributions

“…As shown in Table 2, most of the analyzed works on KG employ a hybrid approach combining more than one recommendation method. Apart from these methods, there are other recommendation approaches that can also be combined with knowledge graphs, e.g., user group recommendation approaches [9,83], conversational approaches [84,85], and social network-based [86,87].…”

Learning Neural Templates for Recommender Dialogue System

“…They release a benchmark dataset REDIAL that collects human conversations about movie recommendation between paired crowd-workers with different roles (i.e., Seeker and Recommender). Further studies (Chen et al, 2019;Zhou et al, 2020a;Ma et al, 2020;Sarkar et al, 2020;Lu et al, 2021) leverage multiple external knowledge bases to enhance the performance of recommendation. propose a multi-goal driven conversation generation framework (MGCG) to proactively and naturally lead a conversation from a nonrecommendation dialogue to a recommendationoriented one.…”

CRFR: Improving Conversational Recommender Systems via Flexible Fragments Reasoning on Knowledge Graphs

“…Flexible Fragments Reasoning. Due to the incompleteness of KG (Sarkar et al, 2020), as a key idea of this work, instead of only modeling user's interest with the destinations of complete reasoning paths, we prefer to model user's interest shift with partial reasoning path, i.e., reasoning fragments.…”

“…Multiple paths in KG help to locate the subspace of the user's interest and generate interpretive utterances in line with people's dialogue behavior, e.g., "...Inception with Christopher Nolan and Leonardo DiCaprio...". However, KGs can not record all relations of interest entities involved in real-world diverse dialogues (Ma et al, 2020;Hayati et al, 2020;Sarkar et al, 2020). Therefore, it is often difficult to achieve a complete reasoning path of interest shift within limited number of hops.…”