Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285735435> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4285735435 endingPage "109471" @default.
- W4285735435 startingPage "109471" @default.
- W4285735435 abstract "As a building block of information retrieval, relation extraction aims at predicting the relation type between two given entities in a piece of text. This task becomes challenging when it is confronted with long text that contains many task-unrelated tokens. Recent attempts to solve this problem have resorted to learning the relatedness among tokens. However, how to obtain appropriate graph for better relatedness representation still remains outstanding, while existing methods have room to improve. In this paper, we propose a novel latent graph learning method to enhance the expressivity of contextual information for the entities of interest. In particular, we design a dual-channel attention mechanism for multi-view graph learning and pool the learned multi-views to sift unrelated tokens for latent graph. This process can be repeated many times for refining the latent structure. We show that our method achieves superior performance on several benchmark datasets, compared to strong baseline models and prior multi-view graph learning approach." @default.
- W4285735435 created "2022-07-18" @default.
- W4285735435 creator A5000608299 @default.
- W4285735435 creator A5005157860 @default.
- W4285735435 creator A5007481575 @default.
- W4285735435 creator A5037458498 @default.
- W4285735435 creator A5038247833 @default.
- W4285735435 creator A5039486014 @default.
- W4285735435 date "2022-09-01" @default.
- W4285735435 modified "2023-09-27" @default.
- W4285735435 title "Latent graph learning with dual-channel attention for relation extraction" @default.
- W4285735435 cites W2064675550 @default.
- W4285735435 cites W2079735306 @default.
- W4285735435 cites W2144354855 @default.
- W4285735435 cites W2475283175 @default.
- W4285735435 cites W2511964075 @default.
- W4285735435 cites W2517194566 @default.
- W4285735435 cites W2586559132 @default.
- W4285735435 cites W2759211898 @default.
- W4285735435 cites W2798393196 @default.
- W4285735435 cites W2892094955 @default.
- W4285735435 cites W2951309718 @default.
- W4285735435 cites W2952768212 @default.
- W4285735435 cites W2970986510 @default.
- W4285735435 cites W2971221499 @default.
- W4285735435 cites W2972505576 @default.
- W4285735435 cites W2984452801 @default.
- W4285735435 cites W2996917304 @default.
- W4285735435 cites W3011411500 @default.
- W4285735435 cites W3034891697 @default.
- W4285735435 cites W3035053871 @default.
- W4285735435 cites W3035566559 @default.
- W4285735435 cites W3104415840 @default.
- W4285735435 cites W3112076981 @default.
- W4285735435 cites W3176214425 @default.
- W4285735435 cites W3176762756 @default.
- W4285735435 cites W4312729759 @default.
- W4285735435 doi "https://doi.org/10.1016/j.knosys.2022.109471" @default.
- W4285735435 hasPublicationYear "2022" @default.
- W4285735435 type Work @default.
- W4285735435 citedByCount "0" @default.
- W4285735435 crossrefType "journal-article" @default.
- W4285735435 hasAuthorship W4285735435A5000608299 @default.
- W4285735435 hasAuthorship W4285735435A5005157860 @default.
- W4285735435 hasAuthorship W4285735435A5007481575 @default.
- W4285735435 hasAuthorship W4285735435A5037458498 @default.
- W4285735435 hasAuthorship W4285735435A5038247833 @default.
- W4285735435 hasAuthorship W4285735435A5039486014 @default.
- W4285735435 hasConcept C119857082 @default.
- W4285735435 hasConcept C124101348 @default.
- W4285735435 hasConcept C132525143 @default.
- W4285735435 hasConcept C153604712 @default.
- W4285735435 hasConcept C154945302 @default.
- W4285735435 hasConcept C195807954 @default.
- W4285735435 hasConcept C25343380 @default.
- W4285735435 hasConcept C41008148 @default.
- W4285735435 hasConcept C80444323 @default.
- W4285735435 hasConceptScore W4285735435C119857082 @default.
- W4285735435 hasConceptScore W4285735435C124101348 @default.
- W4285735435 hasConceptScore W4285735435C132525143 @default.
- W4285735435 hasConceptScore W4285735435C153604712 @default.
- W4285735435 hasConceptScore W4285735435C154945302 @default.
- W4285735435 hasConceptScore W4285735435C195807954 @default.
- W4285735435 hasConceptScore W4285735435C25343380 @default.
- W4285735435 hasConceptScore W4285735435C41008148 @default.
- W4285735435 hasConceptScore W4285735435C80444323 @default.
- W4285735435 hasLocation W42857354351 @default.
- W4285735435 hasOpenAccess W4285735435 @default.
- W4285735435 hasPrimaryLocation W42857354351 @default.
- W4285735435 hasRelatedWork W2528512298 @default.
- W4285735435 hasRelatedWork W2609844752 @default.
- W4285735435 hasRelatedWork W2947903144 @default.
- W4285735435 hasRelatedWork W2949689726 @default.
- W4285735435 hasRelatedWork W2961085424 @default.
- W4285735435 hasRelatedWork W3162501431 @default.
- W4285735435 hasRelatedWork W4285069614 @default.
- W4285735435 hasRelatedWork W4285216485 @default.
- W4285735435 hasRelatedWork W4304700924 @default.
- W4285735435 hasRelatedWork W4306674287 @default.
- W4285735435 hasVolume "252" @default.
- W4285735435 isParatext "false" @default.
- W4285735435 isRetracted "false" @default.
- W4285735435 workType "article" @default.