Matches in SemOpenAlex for { <https://semopenalex.org/work/W3090516735> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3090516735 abstract "Personalized review generation (PRG) aims to automatically produce review text reflecting user preference, which is a challenging natural language generation task. Most of previous studies do not explicitly model factual description of products, tending to generate uninformative content. Moreover, they mainly focus on word-level generation, but cannot accurately reflect more abstractive user preference in multiple aspects. To address the above issues, we propose a novel knowledge-enhanced PRG model based on capsule graph neural network~(Caps-GNN). We first construct a heterogeneous knowledge graph (HKG) for utilizing rich item attributes. We adopt Caps-GNN to learn graph capsules for encoding underlying characteristics from the HKG. Our generation process contains two major steps, namely aspect sequence generation and sentence generation. First, based on graph capsules, we adaptively learn aspect capsules for inferring the aspect sequence. Then, conditioned on the inferred aspect label, we design a graph-based copy mechanism to generate sentences by incorporating related entities or words from HKG. To our knowledge, we are the first to utilize knowledge graph for the PRG task. The incorporated KG information is able to enhance user preference at both aspect and word levels. Extensive experiments on three real-world datasets have demonstrated the effectiveness of our model on the PRG task." @default.
- W3090516735 created "2020-10-08" @default.
- W3090516735 creator A5009911035 @default.
- W3090516735 creator A5025631695 @default.
- W3090516735 creator A5037145565 @default.
- W3090516735 creator A5053345000 @default.
- W3090516735 creator A5071288792 @default.
- W3090516735 creator A5073826103 @default.
- W3090516735 creator A5084365223 @default.
- W3090516735 date "2020-10-19" @default.
- W3090516735 modified "2023-09-25" @default.
- W3090516735 title "Knowledge-Enhanced Personalized Review Generation with Capsule Graph Neural Network" @default.
- W3090516735 cites W2168332560 @default.
- W3090516735 cites W2604314403 @default.
- W3090516735 cites W2740167620 @default.
- W3090516735 cites W2786744843 @default.
- W3090516735 cites W2788919350 @default.
- W3090516735 cites W2883722483 @default.
- W3090516735 cites W2896807716 @default.
- W3090516735 cites W2950404230 @default.
- W3090516735 cites W2963825865 @default.
- W3090516735 cites W2970909388 @default.
- W3090516735 doi "https://doi.org/10.1145/3340531.3411893" @default.
- W3090516735 hasPublicationYear "2020" @default.
- W3090516735 type Work @default.
- W3090516735 sameAs 3090516735 @default.
- W3090516735 citedByCount "12" @default.
- W3090516735 countsByYear W30905167352021 @default.
- W3090516735 countsByYear W30905167352022 @default.
- W3090516735 countsByYear W30905167352023 @default.
- W3090516735 crossrefType "proceedings-article" @default.
- W3090516735 hasAuthorship W3090516735A5009911035 @default.
- W3090516735 hasAuthorship W3090516735A5025631695 @default.
- W3090516735 hasAuthorship W3090516735A5037145565 @default.
- W3090516735 hasAuthorship W3090516735A5053345000 @default.
- W3090516735 hasAuthorship W3090516735A5071288792 @default.
- W3090516735 hasAuthorship W3090516735A5073826103 @default.
- W3090516735 hasAuthorship W3090516735A5084365223 @default.
- W3090516735 hasBestOaLocation W30905167352 @default.
- W3090516735 hasConcept C132525143 @default.
- W3090516735 hasConcept C154945302 @default.
- W3090516735 hasConcept C162324750 @default.
- W3090516735 hasConcept C187736073 @default.
- W3090516735 hasConcept C195324797 @default.
- W3090516735 hasConcept C204321447 @default.
- W3090516735 hasConcept C2776187449 @default.
- W3090516735 hasConcept C2777530160 @default.
- W3090516735 hasConcept C2780451532 @default.
- W3090516735 hasConcept C2987255567 @default.
- W3090516735 hasConcept C2993807640 @default.
- W3090516735 hasConcept C41008148 @default.
- W3090516735 hasConcept C80444323 @default.
- W3090516735 hasConceptScore W3090516735C132525143 @default.
- W3090516735 hasConceptScore W3090516735C154945302 @default.
- W3090516735 hasConceptScore W3090516735C162324750 @default.
- W3090516735 hasConceptScore W3090516735C187736073 @default.
- W3090516735 hasConceptScore W3090516735C195324797 @default.
- W3090516735 hasConceptScore W3090516735C204321447 @default.
- W3090516735 hasConceptScore W3090516735C2776187449 @default.
- W3090516735 hasConceptScore W3090516735C2777530160 @default.
- W3090516735 hasConceptScore W3090516735C2780451532 @default.
- W3090516735 hasConceptScore W3090516735C2987255567 @default.
- W3090516735 hasConceptScore W3090516735C2993807640 @default.
- W3090516735 hasConceptScore W3090516735C41008148 @default.
- W3090516735 hasConceptScore W3090516735C80444323 @default.
- W3090516735 hasLocation W30905167351 @default.
- W3090516735 hasLocation W30905167352 @default.
- W3090516735 hasLocation W30905167353 @default.
- W3090516735 hasOpenAccess W3090516735 @default.
- W3090516735 hasPrimaryLocation W30905167351 @default.
- W3090516735 hasRelatedWork W1573537589 @default.
- W3090516735 hasRelatedWork W159132833 @default.
- W3090516735 hasRelatedWork W2035950535 @default.
- W3090516735 hasRelatedWork W2039844046 @default.
- W3090516735 hasRelatedWork W2401226416 @default.
- W3090516735 hasRelatedWork W3082447286 @default.
- W3090516735 hasRelatedWork W3178985330 @default.
- W3090516735 hasRelatedWork W3200285530 @default.
- W3090516735 hasRelatedWork W3213765460 @default.
- W3090516735 hasRelatedWork W4292482649 @default.
- W3090516735 isParatext "false" @default.
- W3090516735 isRetracted "false" @default.
- W3090516735 magId "3090516735" @default.
- W3090516735 workType "article" @default.