Matches in SemOpenAlex for { <https://semopenalex.org/work/W3213175220> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W3213175220 abstract "Multi-label document classification, associating one document instance with a set of relevant labels, is attracting more and more research attention. Existing methods explore the incorporation of information beyond text, such as document metadata or label structure. These approaches however either simply utilize the semantic information of metadata or employ the predefined parent-child label hierarchy, ignoring the heterogeneous graphical structures of metadata and labels, which we believe are crucial for accurate multi-label document classification. Therefore, in this paper, we propose a novel neural network based approach for multi-label document classification, in which two heterogeneous graphs are constructed and learned using heterogeneous graph transformers. One is metadata heterogeneous graph, which models various types of metadata and their topological relations. The other is label heterogeneous graph, which is constructed based on both the labels’ hierarchy and their statistical dependencies. Experimental results on two benchmark datasets show the proposed approach outperforms several state-of-the-art baselines." @default.
- W3213175220 created "2021-11-22" @default.
- W3213175220 creator A5004191675 @default.
- W3213175220 creator A5007145568 @default.
- W3213175220 creator A5015709853 @default.
- W3213175220 creator A5032749334 @default.
- W3213175220 creator A5061314043 @default.
- W3213175220 date "2021-01-01" @default.
- W3213175220 modified "2023-10-16" @default.
- W3213175220 title "Beyond Text: Incorporating Metadata and Label Structure for Multi-Label Document Classification using Heterogeneous Graphs" @default.
- W3213175220 cites W1997530783 @default.
- W3213175220 cites W2250539671 @default.
- W3213175220 cites W2251292973 @default.
- W3213175220 cites W2362855512 @default.
- W3213175220 cites W2520348554 @default.
- W3213175220 cites W2607041163 @default.
- W3213175220 cites W2739996966 @default.
- W3213175220 cites W2788667846 @default.
- W3213175220 cites W2899313146 @default.
- W3213175220 cites W2911379778 @default.
- W3213175220 cites W2914602134 @default.
- W3213175220 cites W2932399282 @default.
- W3213175220 cites W2962893388 @default.
- W3213175220 cites W2963248507 @default.
- W3213175220 cites W2963341956 @default.
- W3213175220 cites W2963403868 @default.
- W3213175220 cites W2964121744 @default.
- W3213175220 cites W2971092323 @default.
- W3213175220 cites W3012871709 @default.
- W3213175220 cites W3037422790 @default.
- W3213175220 cites W3080994088 @default.
- W3213175220 doi "https://doi.org/10.18653/v1/2021.emnlp-main.253" @default.
- W3213175220 hasPublicationYear "2021" @default.
- W3213175220 type Work @default.
- W3213175220 sameAs 3213175220 @default.
- W3213175220 citedByCount "1" @default.
- W3213175220 countsByYear W32131752202023 @default.
- W3213175220 crossrefType "proceedings-article" @default.
- W3213175220 hasAuthorship W3213175220A5004191675 @default.
- W3213175220 hasAuthorship W3213175220A5007145568 @default.
- W3213175220 hasAuthorship W3213175220A5015709853 @default.
- W3213175220 hasAuthorship W3213175220A5032749334 @default.
- W3213175220 hasAuthorship W3213175220A5061314043 @default.
- W3213175220 hasBestOaLocation W32131752201 @default.
- W3213175220 hasConcept C124101348 @default.
- W3213175220 hasConcept C132525143 @default.
- W3213175220 hasConcept C136764020 @default.
- W3213175220 hasConcept C154945302 @default.
- W3213175220 hasConcept C162324750 @default.
- W3213175220 hasConcept C177264268 @default.
- W3213175220 hasConcept C199360897 @default.
- W3213175220 hasConcept C23123220 @default.
- W3213175220 hasConcept C2776482837 @default.
- W3213175220 hasConcept C31170391 @default.
- W3213175220 hasConcept C34447519 @default.
- W3213175220 hasConcept C41008148 @default.
- W3213175220 hasConcept C80444323 @default.
- W3213175220 hasConcept C93518851 @default.
- W3213175220 hasConceptScore W3213175220C124101348 @default.
- W3213175220 hasConceptScore W3213175220C132525143 @default.
- W3213175220 hasConceptScore W3213175220C136764020 @default.
- W3213175220 hasConceptScore W3213175220C154945302 @default.
- W3213175220 hasConceptScore W3213175220C162324750 @default.
- W3213175220 hasConceptScore W3213175220C177264268 @default.
- W3213175220 hasConceptScore W3213175220C199360897 @default.
- W3213175220 hasConceptScore W3213175220C23123220 @default.
- W3213175220 hasConceptScore W3213175220C2776482837 @default.
- W3213175220 hasConceptScore W3213175220C31170391 @default.
- W3213175220 hasConceptScore W3213175220C34447519 @default.
- W3213175220 hasConceptScore W3213175220C41008148 @default.
- W3213175220 hasConceptScore W3213175220C80444323 @default.
- W3213175220 hasConceptScore W3213175220C93518851 @default.
- W3213175220 hasLocation W32131752201 @default.
- W3213175220 hasOpenAccess W3213175220 @default.
- W3213175220 hasPrimaryLocation W32131752201 @default.
- W3213175220 hasRelatedWork W1515308544 @default.
- W3213175220 hasRelatedWork W1992807924 @default.
- W3213175220 hasRelatedWork W2062427795 @default.
- W3213175220 hasRelatedWork W2313595856 @default.
- W3213175220 hasRelatedWork W2324261804 @default.
- W3213175220 hasRelatedWork W2354642172 @default.
- W3213175220 hasRelatedWork W2360553097 @default.
- W3213175220 hasRelatedWork W2361349944 @default.
- W3213175220 hasRelatedWork W2365800529 @default.
- W3213175220 hasRelatedWork W2775669459 @default.
- W3213175220 isParatext "false" @default.
- W3213175220 isRetracted "false" @default.
- W3213175220 magId "3213175220" @default.
- W3213175220 workType "article" @default.