Topic-enhanced Graph Neural Networks for Extraction-based Explainable Recommendation
Jie Shuai, Le Wu, Kun Zhang, Peijie Sun, Richang Hong, Meng Wang
Abstract
Review information has been demonstrated beneficial for the explainable recommendation. It can be treated as training corpora for generation-based methods or knowledge bases for extraction-based models. However, for generation-based methods, the sparsity of user-generated reviews and the high complexity of generative language models lead to a lack of personalization and adaptability. For extraction-based methods, focusing only on relevant attributes makes them invalid in situations where explicit attribute words are absent, limiting the potential of extraction-based models.
Topics & Concepts
Computer scienceAdaptabilityLimitingPersonalizationGenerative grammarArtificial intelligenceArtificial neural networkMachine learningText generationGraphRecommender systemRelationship extractionInformation extractionInformation retrievalWorld Wide WebTheoretical computer scienceBiologyMechanical engineeringEngineeringEcologyTopic ModelingRecommender Systems and TechniquesAdvanced Graph Neural Networks