Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285268260> ?p ?o ?g. }
- W4285268260 endingPage "75157" @default.
- W4285268260 startingPage "75144" @default.
- W4285268260 abstract "In last years, coreference resolution has received a sensibly performance boost exploiting different pre-trained Neural Language Models, from BERT to SpanBERT until Longformer. This work is aimed at assessing, for the first time, the impact of ELECTRA model on this task, moved by the experimental evidence of an improved contextual representation and better performance on different downstream tasks. In particular, ELECTRA has been employed as representation layer in an assessed neural coreference architecture able to determine entity mentions among spans of text and to best cluster them. The architecture itself has been optimized: i) by simplifying the modality of representation of spans of text but still considering both the context they appear and their entire content, ii) by maximizing both the number and length of input textual segments to exploit better the improved contextual representation power of ELECTRA, iii) by maximizing the number of spans of text to be processed, since potentially representing mentions, preserving computational efficiency. Experimental results on the OntoNotes dataset have shown the effectiveness of this solution from both a quantitative and qualitative perspective, and also with respect to other state-of-the-art models, thanks to a more proficient token and span representation. The results also hint at the possible use of this solution also for low-resource languages, simply requiring a pre-trained version of ELECTRA instead of language-specific models trained to handle either spans of text or long documents." @default.
- W4285268260 created "2022-07-14" @default.
- W4285268260 creator A5004593198 @default.
- W4285268260 creator A5011417253 @default.
- W4285268260 creator A5025157025 @default.
- W4285268260 creator A5038855081 @default.
- W4285268260 creator A5042597849 @default.
- W4285268260 creator A5068426842 @default.
- W4285268260 creator A5086794713 @default.
- W4285268260 date "2022-01-01" @default.
- W4285268260 modified "2023-10-14" @default.
- W4285268260 title "An ELECTRA-Based Model for Neural Coreference Resolution" @default.
- W4285268260 cites W2251064706 @default.
- W4285268260 cites W2949493644 @default.
- W4285268260 cites W2950217500 @default.
- W4285268260 cites W2962769558 @default.
- W4285268260 cites W2963087868 @default.
- W4285268260 cites W2963167649 @default.
- W4285268260 cites W2963695529 @default.
- W4285268260 cites W2964222246 @default.
- W4285268260 cites W2970550868 @default.
- W4285268260 cites W2981004913 @default.
- W4285268260 cites W3003276437 @default.
- W4285268260 cites W3011411500 @default.
- W4285268260 cites W3034797437 @default.
- W4285268260 cites W3081056948 @default.
- W4285268260 cites W3098264558 @default.
- W4285268260 cites W3118485687 @default.
- W4285268260 cites W3174331410 @default.
- W4285268260 cites W3175081470 @default.
- W4285268260 cites W3179195481 @default.
- W4285268260 doi "https://doi.org/10.1109/access.2022.3189956" @default.
- W4285268260 hasPublicationYear "2022" @default.
- W4285268260 type Work @default.
- W4285268260 citedByCount "1" @default.
- W4285268260 countsByYear W42852682602023 @default.
- W4285268260 crossrefType "journal-article" @default.
- W4285268260 hasAuthorship W4285268260A5004593198 @default.
- W4285268260 hasAuthorship W4285268260A5011417253 @default.
- W4285268260 hasAuthorship W4285268260A5025157025 @default.
- W4285268260 hasAuthorship W4285268260A5038855081 @default.
- W4285268260 hasAuthorship W4285268260A5042597849 @default.
- W4285268260 hasAuthorship W4285268260A5068426842 @default.
- W4285268260 hasAuthorship W4285268260A5086794713 @default.
- W4285268260 hasBestOaLocation W42852682601 @default.
- W4285268260 hasConcept C119857082 @default.
- W4285268260 hasConcept C12713177 @default.
- W4285268260 hasConcept C137293760 @default.
- W4285268260 hasConcept C138268822 @default.
- W4285268260 hasConcept C151730666 @default.
- W4285268260 hasConcept C154945302 @default.
- W4285268260 hasConcept C162324750 @default.
- W4285268260 hasConcept C17744445 @default.
- W4285268260 hasConcept C187736073 @default.
- W4285268260 hasConcept C199539241 @default.
- W4285268260 hasConcept C204321447 @default.
- W4285268260 hasConcept C2776359362 @default.
- W4285268260 hasConcept C2779343474 @default.
- W4285268260 hasConcept C2780451532 @default.
- W4285268260 hasConcept C28076734 @default.
- W4285268260 hasConcept C38652104 @default.
- W4285268260 hasConcept C41008148 @default.
- W4285268260 hasConcept C48145219 @default.
- W4285268260 hasConcept C86803240 @default.
- W4285268260 hasConcept C94625758 @default.
- W4285268260 hasConceptScore W4285268260C119857082 @default.
- W4285268260 hasConceptScore W4285268260C12713177 @default.
- W4285268260 hasConceptScore W4285268260C137293760 @default.
- W4285268260 hasConceptScore W4285268260C138268822 @default.
- W4285268260 hasConceptScore W4285268260C151730666 @default.
- W4285268260 hasConceptScore W4285268260C154945302 @default.
- W4285268260 hasConceptScore W4285268260C162324750 @default.
- W4285268260 hasConceptScore W4285268260C17744445 @default.
- W4285268260 hasConceptScore W4285268260C187736073 @default.
- W4285268260 hasConceptScore W4285268260C199539241 @default.
- W4285268260 hasConceptScore W4285268260C204321447 @default.
- W4285268260 hasConceptScore W4285268260C2776359362 @default.
- W4285268260 hasConceptScore W4285268260C2779343474 @default.
- W4285268260 hasConceptScore W4285268260C2780451532 @default.
- W4285268260 hasConceptScore W4285268260C28076734 @default.
- W4285268260 hasConceptScore W4285268260C38652104 @default.
- W4285268260 hasConceptScore W4285268260C41008148 @default.
- W4285268260 hasConceptScore W4285268260C48145219 @default.
- W4285268260 hasConceptScore W4285268260C86803240 @default.
- W4285268260 hasConceptScore W4285268260C94625758 @default.
- W4285268260 hasLocation W42852682601 @default.
- W4285268260 hasLocation W42852682602 @default.
- W4285268260 hasLocation W42852682603 @default.
- W4285268260 hasOpenAccess W4285268260 @default.
- W4285268260 hasPrimaryLocation W42852682601 @default.
- W4285268260 hasRelatedWork W1578225302 @default.
- W4285268260 hasRelatedWork W2067779294 @default.
- W4285268260 hasRelatedWork W2134973266 @default.
- W4285268260 hasRelatedWork W2252140686 @default.
- W4285268260 hasRelatedWork W2379250586 @default.
- W4285268260 hasRelatedWork W2740062997 @default.
- W4285268260 hasRelatedWork W2769923147 @default.
- W4285268260 hasRelatedWork W2820779948 @default.