FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3112076981> ?p ?o ?g. }

• W3112076981 endingPage "14202" @default.
• W3112076981 startingPage "14194" @default.
• W3112076981 abstract "Relation Extraction (RE) is to predict the relation type of two entities that are mentioned in a piece of text, e.g., a sentence or a dialogue. When the given text is long, it is challenging to identify indicative words for the relation prediction. Recent advances on RE task are from BERT-based sequence modeling and graph-based modeling of relationships among the tokens in the sequence. In this paper, we propose to construct a latent multi-view graph to capture various possible relationships among tokens. We then refine this graph to select important words for relation prediction. Finally, the representation of the refined graph and the BERT-based sequence representation are concatenated for relation extraction. Specifically, in our proposed GDPNet (Gaussian Dynamic Time Warping Pooling Net), we utilize Gaussian Graph Generator (GGG) to generate edges of the multi-view graph. The graph is then refined by Dynamic Time Warping Pooling (DTWPool). On DialogRE and TACRED, we show that GDPNet achieves the best performance on dialogue-level RE, and comparable performance with the state-of-the-arts on sentence-level RE." @default.
• W3112076981 created "2020-12-21" @default.
• W3112076981 creator A5005151737 @default.
• W3112076981 creator A5007460835 @default.
• W3112076981 creator A5041413629 @default.
• W3112076981 creator A5049341927 @default.
• W3112076981 date "2021-05-18" @default.
• W3112076981 modified "2023-10-14" @default.
• W3112076981 title "GDPNet: Refining Latent Multi-View Graph for Relation Extraction" @default.
• W3112076981 cites W2064675550 @default.
• W3112076981 cites W2073587810 @default.
• W3112076981 cites W2144354855 @default.
• W3112076981 cites W2251091211 @default.
• W3112076981 cites W2517194566 @default.
• W3112076981 cites W2586559132 @default.
• W3112076981 cites W2759211898 @default.
• W3112076981 cites W2798393196 @default.
• W3112076981 cites W2811124557 @default.
• W3112076981 cites W2892094955 @default.
• W3112076981 cites W2952768212 @default.
• W3112076981 cites W2952832237 @default.
• W3112076981 cites W2963175980 @default.
• W3112076981 cites W2963341956 @default.
• W3112076981 cites W2963405869 @default.
• W3112076981 cites W2963984147 @default.
• W3112076981 cites W2964121744 @default.
• W3112076981 cites W2964349647 @default.
• W3112076981 cites W2970986510 @default.
• W3112076981 cites W2971221499 @default.
• W3112076981 cites W2984452801 @default.
• W3112076981 cites W2996091850 @default.
• W3112076981 cites W2996917304 @default.
• W3112076981 cites W3011411500 @default.
• W3112076981 cites W3034497660 @default.
• W3112076981 cites W3034891697 @default.
• W3112076981 cites W3035053871 @default.
• W3112076981 cites W3023071679 @default.
• W3112076981 doi "https://doi.org/10.1609/aaai.v35i16.17670" @default.
• W3112076981 hasPublicationYear "2021" @default.
• W3112076981 type Work @default.
• W3112076981 sameAs 3112076981 @default.
• W3112076981 citedByCount "19" @default.
• W3112076981 countsByYear W31120769812021 @default.
• W3112076981 countsByYear W31120769812022 @default.
• W3112076981 countsByYear W31120769812023 @default.
• W3112076981 crossrefType "journal-article" @default.
• W3112076981 hasAuthorship W3112076981A5005151737 @default.
• W3112076981 hasAuthorship W3112076981A5007460835 @default.
• W3112076981 hasAuthorship W3112076981A5041413629 @default.
• W3112076981 hasAuthorship W3112076981A5049341927 @default.
• W3112076981 hasBestOaLocation W31120769811 @default.
• W3112076981 hasConcept C121332964 @default.
• W3112076981 hasConcept C124101348 @default.
• W3112076981 hasConcept C132525143 @default.
• W3112076981 hasConcept C153180895 @default.
• W3112076981 hasConcept C153604712 @default.
• W3112076981 hasConcept C154945302 @default.
• W3112076981 hasConcept C163716315 @default.
• W3112076981 hasConcept C204321447 @default.
• W3112076981 hasConcept C25343380 @default.
• W3112076981 hasConcept C2777530160 @default.
• W3112076981 hasConcept C41008148 @default.
• W3112076981 hasConcept C62520636 @default.
• W3112076981 hasConcept C70437156 @default.
• W3112076981 hasConcept C80444323 @default.
• W3112076981 hasConceptScore W3112076981C121332964 @default.
• W3112076981 hasConceptScore W3112076981C124101348 @default.
• W3112076981 hasConceptScore W3112076981C132525143 @default.
• W3112076981 hasConceptScore W3112076981C153180895 @default.
• W3112076981 hasConceptScore W3112076981C153604712 @default.
• W3112076981 hasConceptScore W3112076981C154945302 @default.
• W3112076981 hasConceptScore W3112076981C163716315 @default.
• W3112076981 hasConceptScore W3112076981C204321447 @default.
• W3112076981 hasConceptScore W3112076981C25343380 @default.
• W3112076981 hasConceptScore W3112076981C2777530160 @default.
• W3112076981 hasConceptScore W3112076981C41008148 @default.
• W3112076981 hasConceptScore W3112076981C62520636 @default.
• W3112076981 hasConceptScore W3112076981C70437156 @default.
• W3112076981 hasConceptScore W3112076981C80444323 @default.
• W3112076981 hasIssue "16" @default.
• W3112076981 hasLocation W31120769811 @default.
• W3112076981 hasLocation W31120769812 @default.
• W3112076981 hasLocation W31120769813 @default.
• W3112076981 hasOpenAccess W3112076981 @default.
• W3112076981 hasPrimaryLocation W31120769811 @default.
• W3112076981 hasRelatedWork W147410782 @default.
• W3112076981 hasRelatedWork W2626256601 @default.
• W3112076981 hasRelatedWork W2805262146 @default.
• W3112076981 hasRelatedWork W2900413183 @default.
• W3112076981 hasRelatedWork W2953234277 @default.
• W3112076981 hasRelatedWork W3015684221 @default.
• W3112076981 hasRelatedWork W3022252430 @default.
• W3112076981 hasRelatedWork W4287804464 @default.
• W3112076981 hasRelatedWork W4287816705 @default.
• W3112076981 hasRelatedWork W4379517534 @default.
• W3112076981 hasVolume "35" @default.
• W3112076981 isParatext "false" @default.
• W3112076981 isRetracted "false" @default.

• next