Matches in SemOpenAlex for { <https://semopenalex.org/work/W3045744218> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W3045744218 endingPage "26" @default.
- W3045744218 startingPage "15" @default.
- W3045744218 abstract "Abstract More and more attention has been paid to automatic keyphrase generation as it facilitates a wide variety of downstream AI applications, such as information retrieval, text summarization and opinion mining. Although sequence-to-sequence architecture with attention and copy mechanisms (CopyNet) to this task shows promising results, it still suffered from the following shortcomings: (i) it only encodes the keyphrase (usually consists of several words) in word level which can not adequately capture the overall meaning of keyphrase; (ii) it lacks a suitable way to model the correlation among different keyphrases which is very helpful for generating richer and more comprehensive candidate phrases. To overcome these challenges, a novel keyphrase generation model named Hierarchical CopyNet with graph attention networks (HCopy-GAT) is proposed. Firstly, the Hierarchical Recurrent Encode-Decoder neural network (HRED) is employed to learn the expressive embeddings of keyphrases in both word-level and phrase-level. Secondly, the graph attention neural networks (GAT) is applied to model the correlation among different keyphrases. Furthermore, we developed a new dataset named SOFTWARE, which can be taken as a new testbed for keyword generation tasks. With empirical experiments on several real datasets (including our newly built dataset), the proposed HCopy-GAT model outperforms state-of-the-art keyphrase generation models." @default.
- W3045744218 created "2020-08-03" @default.
- W3045744218 creator A5011791047 @default.
- W3045744218 creator A5026821474 @default.
- W3045744218 creator A5040367916 @default.
- W3045744218 creator A5059732979 @default.
- W3045744218 creator A5078083652 @default.
- W3045744218 date "2020-11-01" @default.
- W3045744218 modified "2023-09-24" @default.
- W3045744218 title "Co-occurrence graph based hierarchical neural networks for keyphrase generation" @default.
- W3045744218 cites W1993378086 @default.
- W3045744218 cites W2030903088 @default.
- W3045744218 cites W2116341502 @default.
- W3045744218 cites W2136542423 @default.
- W3045744218 cites W2150815390 @default.
- W3045744218 cites W2317515691 @default.
- W3045744218 cites W2559152380 @default.
- W3045744218 cites W2568273639 @default.
- W3045744218 cites W2593560537 @default.
- W3045744218 cites W2606974598 @default.
- W3045744218 cites W2888766462 @default.
- W3045744218 cites W2932847124 @default.
- W3045744218 cites W2949647400 @default.
- W3045744218 cites W2949877232 @default.
- W3045744218 cites W2949963192 @default.
- W3045744218 cites W2954579984 @default.
- W3045744218 cites W2962883855 @default.
- W3045744218 cites W2963265326 @default.
- W3045744218 cites W2963275829 @default.
- W3045744218 cites W2963341956 @default.
- W3045744218 cites W2963531963 @default.
- W3045744218 cites W2963879591 @default.
- W3045744218 cites W3022187094 @default.
- W3045744218 cites W4288280762 @default.
- W3045744218 doi "https://doi.org/10.1016/j.neucom.2020.07.084" @default.
- W3045744218 hasPublicationYear "2020" @default.
- W3045744218 type Work @default.
- W3045744218 sameAs 3045744218 @default.
- W3045744218 citedByCount "2" @default.
- W3045744218 countsByYear W30457442182021 @default.
- W3045744218 crossrefType "journal-article" @default.
- W3045744218 hasAuthorship W3045744218A5011791047 @default.
- W3045744218 hasAuthorship W3045744218A5026821474 @default.
- W3045744218 hasAuthorship W3045744218A5040367916 @default.
- W3045744218 hasAuthorship W3045744218A5059732979 @default.
- W3045744218 hasAuthorship W3045744218A5078083652 @default.
- W3045744218 hasConcept C132525143 @default.
- W3045744218 hasConcept C154945302 @default.
- W3045744218 hasConcept C41008148 @default.
- W3045744218 hasConcept C50644808 @default.
- W3045744218 hasConcept C80444323 @default.
- W3045744218 hasConceptScore W3045744218C132525143 @default.
- W3045744218 hasConceptScore W3045744218C154945302 @default.
- W3045744218 hasConceptScore W3045744218C41008148 @default.
- W3045744218 hasConceptScore W3045744218C50644808 @default.
- W3045744218 hasConceptScore W3045744218C80444323 @default.
- W3045744218 hasLocation W30457442181 @default.
- W3045744218 hasOpenAccess W3045744218 @default.
- W3045744218 hasPrimaryLocation W30457442181 @default.
- W3045744218 hasRelatedWork W2107367999 @default.
- W3045744218 hasRelatedWork W2159443810 @default.
- W3045744218 hasRelatedWork W2386387936 @default.
- W3045744218 hasRelatedWork W2391817034 @default.
- W3045744218 hasRelatedWork W2801014462 @default.
- W3045744218 hasRelatedWork W3001020386 @default.
- W3045744218 hasRelatedWork W3107474891 @default.
- W3045744218 hasRelatedWork W4317504855 @default.
- W3045744218 hasRelatedWork W644753246 @default.
- W3045744218 hasRelatedWork W1629725936 @default.
- W3045744218 hasVolume "415" @default.
- W3045744218 isParatext "false" @default.
- W3045744218 isRetracted "false" @default.
- W3045744218 magId "3045744218" @default.
- W3045744218 workType "article" @default.