SkipCor: skip-mention coreference resolution using linear-chain conditional random fields.

Coreference resolution tries to identify all expressions (called mentions) in observed text that refer to the same entity. Beside entity extraction and relation extraction, it represents one of the three complementary tasks in Information Extraction. In this paper we describe a novel coreference res...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Slavko Žitnik, Lovro Šubelj, Marko Bajec
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2014
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/a91164fb3295416f83e05b415bff07ec
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a91164fb3295416f83e05b415bff07ec
record_format	dspace
spelling	oai:doaj.org-article:a91164fb3295416f83e05b415bff07ec2021-11-18T08:14:39ZSkipCor: skip-mention coreference resolution using linear-chain conditional random fields.1932-620310.1371/journal.pone.0100101https://doaj.org/article/a91164fb3295416f83e05b415bff07ec2014-01-01T00:00:00Zhttps://www.ncbi.nlm.nih.gov/pmc/articles/pmid/24956272/?tool=EBIhttps://doaj.org/toc/1932-6203Coreference resolution tries to identify all expressions (called mentions) in observed text that refer to the same entity. Beside entity extraction and relation extraction, it represents one of the three complementary tasks in Information Extraction. In this paper we describe a novel coreference resolution system SkipCor that reformulates the problem as a sequence labeling task. None of the existing supervised, unsupervised, pairwise or sequence-based models are similar to our approach, which only uses linear-chain conditional random fields and supports high scalability with fast model training and inference, and a straightforward parallelization. We evaluate the proposed system against the ACE 2004, CoNLL 2012 and SemEval 2010 benchmark datasets. SkipCor clearly outperforms two baseline systems that detect coreferentiality using the same features as SkipCor. The obtained results are at least comparable to the current state-of-the-art in coreference resolution.Slavko ŽitnikLovro ŠubeljMarko BajecPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 9, Iss 6, p e100101 (2014)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Slavko Žitnik Lovro Šubelj Marko Bajec SkipCor: skip-mention coreference resolution using linear-chain conditional random fields.
description	Coreference resolution tries to identify all expressions (called mentions) in observed text that refer to the same entity. Beside entity extraction and relation extraction, it represents one of the three complementary tasks in Information Extraction. In this paper we describe a novel coreference resolution system SkipCor that reformulates the problem as a sequence labeling task. None of the existing supervised, unsupervised, pairwise or sequence-based models are similar to our approach, which only uses linear-chain conditional random fields and supports high scalability with fast model training and inference, and a straightforward parallelization. We evaluate the proposed system against the ACE 2004, CoNLL 2012 and SemEval 2010 benchmark datasets. SkipCor clearly outperforms two baseline systems that detect coreferentiality using the same features as SkipCor. The obtained results are at least comparable to the current state-of-the-art in coreference resolution.
format	article
author	Slavko Žitnik Lovro Šubelj Marko Bajec
author_facet	Slavko Žitnik Lovro Šubelj Marko Bajec
author_sort	Slavko Žitnik
title	SkipCor: skip-mention coreference resolution using linear-chain conditional random fields.
title_short	SkipCor: skip-mention coreference resolution using linear-chain conditional random fields.
title_full	SkipCor: skip-mention coreference resolution using linear-chain conditional random fields.
title_fullStr	SkipCor: skip-mention coreference resolution using linear-chain conditional random fields.
title_full_unstemmed	SkipCor: skip-mention coreference resolution using linear-chain conditional random fields.
title_sort	skipcor: skip-mention coreference resolution using linear-chain conditional random fields.
publisher	Public Library of Science (PLoS)
publishDate	2014
url	https://doaj.org/article/a91164fb3295416f83e05b415bff07ec
work_keys_str_mv	AT slavkozitnik skipcorskipmentioncoreferenceresolutionusinglinearchainconditionalrandomfields AT lovrosubelj skipcorskipmentioncoreferenceresolutionusinglinearchainconditionalrandomfields AT markobajec skipcorskipmentioncoreferenceresolutionusinglinearchainconditionalrandomfields
_version_	1718422003367542784

SkipCor: skip-mention coreference resolution using linear-chain conditional random fields.

Ejemplares similares