Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion
Kun Zhou, Wayne Xin Zhao, Shuqing Bian, Yuanhang Zhou, Ji-Rong Wen, Jingsong Yu
Abstract
Conversational recommender systems (CRS) aim to recommend high-quality items to users through interactive conversations. Although several efforts have been made for CRS, two major issues still remain to be solved. First, the conversation data itself lacks of sufficient contextual information for accurately understanding users' preference. Second, there is a semantic gap between natural language expression and item-level user preference.
Topics & Concepts
Computer scienceRecommender systemConversationPreferenceInformation retrievalNatural language processingGraphNatural languageSemantic gapArtificial intelligenceKnowledge graphQuality (philosophy)Semantics (computer science)Human–computer interactionWorld Wide WebTheoretical computer scienceMicroeconomicsEconomicsImage (mathematics)Image retrievalPhilosophyEpistemologyLinguisticsProgramming languageRecommender Systems and TechniquesTopic ModelingAdvanced Graph Neural Networks