Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210270770> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4210270770 endingPage "363" @default.
- W4210270770 startingPage "355" @default.
- W4210270770 abstract "Personalized news recommendation is becoming increasingly important for online news platforms to help users alleviate information overload and improve news reading experience. A key problem in news recommendation is learning accurate user representations to capture their interest. However, most existing news recommendation methods usually learn user representation only from their interacted historical news, while ignoring the clustering features among users. Here we proposed a hierarchical user preference hash network to enhance the representation of users' interest. In the hash part, a series of buckets are generated based on users' historical interactions. Users with similar preferences are assigned into the same buckets automatically. We also learn representations of users from their browsed news in history part. And then, a Route Attention is adopted to combine these two parts (history vector and hash vector) and get the more informative user preference vector. As for news representation, a modified transformer with category embedding is exploited to build news semantic representation. By comparing the hierarchical hash network with multiple news recommendation methods and conducting various experiments on the Microsoft News Dataset (MIND) validate the effectiveness of our approach on news recommendation." @default.
- W4210270770 created "2022-02-08" @default.
- W4210270770 creator A5017041578 @default.
- W4210270770 creator A5056722570 @default.
- W4210270770 creator A5080102032 @default.
- W4210270770 creator A5086165797 @default.
- W4210270770 date "2022-02-01" @default.
- W4210270770 modified "2023-09-24" @default.
- W4210270770 title "Hierarchical Preference Hash Network for News Recommendation" @default.
- W4210270770 cites W2076538105 @default.
- W4210270770 cites W2094286023 @default.
- W4210270770 cites W2109421086 @default.
- W4210270770 cites W2136189984 @default.
- W4210270770 cites W2153111836 @default.
- W4210270770 cites W2250539671 @default.
- W4210270770 cites W2475334473 @default.
- W4210270770 cites W2604662567 @default.
- W4210270770 cites W2742272831 @default.
- W4210270770 cites W2903803738 @default.
- W4210270770 cites W2950416834 @default.
- W4210270770 cites W2950421571 @default.
- W4210270770 cites W2963869731 @default.
- W4210270770 cites W2964536660 @default.
- W4210270770 cites W2970793364 @default.
- W4210270770 cites W3014828506 @default.
- W4210270770 cites W3034503922 @default.
- W4210270770 cites W3034707247 @default.
- W4210270770 doi "https://doi.org/10.1587/transinf.2021edp7034" @default.
- W4210270770 hasPublicationYear "2022" @default.
- W4210270770 type Work @default.
- W4210270770 citedByCount "0" @default.
- W4210270770 crossrefType "journal-article" @default.
- W4210270770 hasAuthorship W4210270770A5017041578 @default.
- W4210270770 hasAuthorship W4210270770A5056722570 @default.
- W4210270770 hasAuthorship W4210270770A5080102032 @default.
- W4210270770 hasAuthorship W4210270770A5086165797 @default.
- W4210270770 hasBestOaLocation W42102707701 @default.
- W4210270770 hasConcept C119857082 @default.
- W4210270770 hasConcept C136764020 @default.
- W4210270770 hasConcept C162324750 @default.
- W4210270770 hasConcept C175444787 @default.
- W4210270770 hasConcept C17744445 @default.
- W4210270770 hasConcept C186625053 @default.
- W4210270770 hasConcept C199539241 @default.
- W4210270770 hasConcept C23123220 @default.
- W4210270770 hasConcept C26517878 @default.
- W4210270770 hasConcept C2776359362 @default.
- W4210270770 hasConcept C2781249084 @default.
- W4210270770 hasConcept C38652104 @default.
- W4210270770 hasConcept C41008148 @default.
- W4210270770 hasConcept C59404180 @default.
- W4210270770 hasConcept C94625758 @default.
- W4210270770 hasConcept C99138194 @default.
- W4210270770 hasConceptScore W4210270770C119857082 @default.
- W4210270770 hasConceptScore W4210270770C136764020 @default.
- W4210270770 hasConceptScore W4210270770C162324750 @default.
- W4210270770 hasConceptScore W4210270770C175444787 @default.
- W4210270770 hasConceptScore W4210270770C17744445 @default.
- W4210270770 hasConceptScore W4210270770C186625053 @default.
- W4210270770 hasConceptScore W4210270770C199539241 @default.
- W4210270770 hasConceptScore W4210270770C23123220 @default.
- W4210270770 hasConceptScore W4210270770C26517878 @default.
- W4210270770 hasConceptScore W4210270770C2776359362 @default.
- W4210270770 hasConceptScore W4210270770C2781249084 @default.
- W4210270770 hasConceptScore W4210270770C38652104 @default.
- W4210270770 hasConceptScore W4210270770C41008148 @default.
- W4210270770 hasConceptScore W4210270770C59404180 @default.
- W4210270770 hasConceptScore W4210270770C94625758 @default.
- W4210270770 hasConceptScore W4210270770C99138194 @default.
- W4210270770 hasIssue "2" @default.
- W4210270770 hasLocation W42102707701 @default.
- W4210270770 hasOpenAccess W4210270770 @default.
- W4210270770 hasPrimaryLocation W42102707701 @default.
- W4210270770 hasRelatedWork W1518202215 @default.
- W4210270770 hasRelatedWork W2086064646 @default.
- W4210270770 hasRelatedWork W2093597205 @default.
- W4210270770 hasRelatedWork W2119135658 @default.
- W4210270770 hasRelatedWork W2329452785 @default.
- W4210270770 hasRelatedWork W2356380379 @default.
- W4210270770 hasRelatedWork W2357241418 @default.
- W4210270770 hasRelatedWork W2363925233 @default.
- W4210270770 hasRelatedWork W2748952813 @default.
- W4210270770 hasRelatedWork W3041052722 @default.
- W4210270770 hasVolume "E105.D" @default.
- W4210270770 isParatext "false" @default.
- W4210270770 isRetracted "false" @default.
- W4210270770 workType "article" @default.