Please use this identifier to cite or link to this item: https://hdl.handle.net/10216/123609
Full metadata record
DC FieldValueLanguage
dc.creatorAndré Ferreira Cruz
dc.creatorGil Rocha
dc.creatorHenrique Lopes Cardoso
dc.date.accessioned2020-09-16T23:06:34Z-
dc.date.available2020-09-16T23:06:34Z-
dc.date.issued2018
dc.identifier.othersigarra:363697
dc.identifier.urihttps://hdl.handle.net/10216/123609-
dc.description.abstractThe task of coreference resolution has attracted a great deal of attention in the literature due to its importance in deep language understanding, and its potential as a subtask in a variety of complex natural language processing problems. We experiment with different methods for generating training data and architectures for extracting meaningful mention representations. Coreference resolution in lesser-resourced languages is challenging, and transfer learning is a promising technique to overcome the comparatively smaller available corpora. We explore direct transfer learning from Spanish to Portuguese. We present state-of-the-art systems on both Spanish and Portuguese, and report promising results in a cross-language setting. (c) 2018 IEEE.
dc.language.isoeng
dc.relation.ispartof2018 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018
dc.rightsopenAccess
dc.titleExploring Spanish Corpora for Portuguese Coreference Resolution
dc.typeArtigo em Livro de Atas de Conferência Internacional
dc.contributor.uportoFaculdade de Engenharia
dc.identifier.doi10.1109/snams.2018.8554705
dc.identifier.authenticusP-00Q-44H
Appears in Collections:FEUP - Artigo em Livro de Atas de Conferência Internacional

Files in This Item:
File Description SizeFormat 
363697.pdf801.3 kBAdobe PDFThumbnail
View/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.