Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385570082> ?p ?o ?g. }
Showing items 1 to 59 of
59
with 100 items per page.
- W4385570082 abstract "Entity coreference resolution is an important research problem with many applications, including information extraction and question answering. Coreference resolution for English has been studied extensively. However, there is relatively little work for other languages. A problem that frequently occurs when working with a non-English language is the scarcity of annotated training data. To overcome this challenge, we design a simple but effective ensemble-based framework that combines various transfer learning (TL) techniques. We first train several models using different TL methods. Then, during inference, we compute the unweighted average scores of the models’ predictions to extract the final set of predicted clusters. Furthermore, we also propose a low-cost TL method that bootstraps coreference resolution models by utilizing Wikipedia anchor texts. Leveraging the idea that the coreferential links naturally exist between anchor texts pointing to the same article, our method builds a sizeable distantly-supervised dataset for the target language that consists of tens of thousands of documents. We can pre-train a model on the pseudo-labeled dataset before finetuning it on the final target dataset. Experimental results on two benchmark datasets, OntoNotes and SemEval, confirm the effectiveness of our methods. Our best ensembles consistently outperform the baseline approach of simple training by up to 7.68% in the F1 score. These ensembles also achieve new state-of-the-art results for three languages: Arabic, Dutch, and Spanish." @default.
- W4385570082 created "2023-08-05" @default.
- W4385570082 creator A5036250098 @default.
- W4385570082 creator A5075033889 @default.
- W4385570082 date "2023-01-01" @default.
- W4385570082 modified "2023-09-23" @default.
- W4385570082 title "Ensemble Transfer Learning for Multilingual Coreference Resolution" @default.
- W4385570082 doi "https://doi.org/10.18653/v1/2023.codi-1.3" @default.
- W4385570082 hasPublicationYear "2023" @default.
- W4385570082 type Work @default.
- W4385570082 citedByCount "0" @default.
- W4385570082 crossrefType "proceedings-article" @default.
- W4385570082 hasAuthorship W4385570082A5036250098 @default.
- W4385570082 hasAuthorship W4385570082A5075033889 @default.
- W4385570082 hasBestOaLocation W43855700821 @default.
- W4385570082 hasConcept C119857082 @default.
- W4385570082 hasConcept C13280743 @default.
- W4385570082 hasConcept C138268822 @default.
- W4385570082 hasConcept C150899416 @default.
- W4385570082 hasConcept C154945302 @default.
- W4385570082 hasConcept C177264268 @default.
- W4385570082 hasConcept C185798385 @default.
- W4385570082 hasConcept C199360897 @default.
- W4385570082 hasConcept C204321447 @default.
- W4385570082 hasConcept C205649164 @default.
- W4385570082 hasConcept C2776214188 @default.
- W4385570082 hasConcept C28076734 @default.
- W4385570082 hasConcept C41008148 @default.
- W4385570082 hasConcept C51632099 @default.
- W4385570082 hasConceptScore W4385570082C119857082 @default.
- W4385570082 hasConceptScore W4385570082C13280743 @default.
- W4385570082 hasConceptScore W4385570082C138268822 @default.
- W4385570082 hasConceptScore W4385570082C150899416 @default.
- W4385570082 hasConceptScore W4385570082C154945302 @default.
- W4385570082 hasConceptScore W4385570082C177264268 @default.
- W4385570082 hasConceptScore W4385570082C185798385 @default.
- W4385570082 hasConceptScore W4385570082C199360897 @default.
- W4385570082 hasConceptScore W4385570082C204321447 @default.
- W4385570082 hasConceptScore W4385570082C205649164 @default.
- W4385570082 hasConceptScore W4385570082C2776214188 @default.
- W4385570082 hasConceptScore W4385570082C28076734 @default.
- W4385570082 hasConceptScore W4385570082C41008148 @default.
- W4385570082 hasConceptScore W4385570082C51632099 @default.
- W4385570082 hasLocation W43855700821 @default.
- W4385570082 hasOpenAccess W4385570082 @default.
- W4385570082 hasPrimaryLocation W43855700821 @default.
- W4385570082 hasRelatedWork W1578225302 @default.
- W4385570082 hasRelatedWork W2108505829 @default.
- W4385570082 hasRelatedWork W2134973266 @default.
- W4385570082 hasRelatedWork W2252140686 @default.
- W4385570082 hasRelatedWork W2379250586 @default.
- W4385570082 hasRelatedWork W2820779948 @default.
- W4385570082 hasRelatedWork W3031383011 @default.
- W4385570082 hasRelatedWork W4288040045 @default.
- W4385570082 hasRelatedWork W4308672463 @default.
- W4385570082 hasRelatedWork W54903681 @default.
- W4385570082 isParatext "false" @default.
- W4385570082 isRetracted "false" @default.
- W4385570082 workType "article" @default.