Graph-Based Bootstrapping for Coreference Resolution
Coreference resolution is a challenging natural language processing task, and it is difficult to identify the correct mentions of an entity that can be any noun or noun phrase. In this article, a semisupervised, two-stage pattern-based bootstrapping approach is proposed for the coreference resolutio...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
De Gruyter
2014-09-01
|
Series: | Journal of Intelligent Systems |
Subjects: | |
Online Access: | https://doi.org/10.1515/jisys-2013-0056 |
id |
doaj-10452f734239498e9faafad3269a6b19 |
---|---|
record_format |
Article |
spelling |
doaj-10452f734239498e9faafad3269a6b192021-09-06T19:40:35ZengDe GruyterJournal of Intelligent Systems0334-18602191-026X2014-09-0123329331010.1515/jisys-2013-0056Graph-Based Bootstrapping for Coreference ResolutionBalaji J.0Geetha T.V.1Ranjani P.2Department of Computer Science and Engineering, Anna University, Chennai, Tamil Nadu, IndiaDepartment of Computer Science and Engineering, Anna University, Chennai, Tamil Nadu, IndiaDepartment of Information Science and Technology, Anna University, Chennai, Tamil Nadu, IndiaCoreference resolution is a challenging natural language processing task, and it is difficult to identify the correct mentions of an entity that can be any noun or noun phrase. In this article, a semisupervised, two-stage pattern-based bootstrapping approach is proposed for the coreference resolution task. During Stage 1, the possible mentions are identified using word-based features, and during Stage 2, the correct mentions are identified by filtering the non-coreferents of an entity using statistical measures and graph-based features. Whereas the existing approaches use morphosyntactic and number/gender agreement features, the proposed approach uses semantic graph-based context-level semantics and nested noun phrases in the correct mentions identification. Moreover, mentions without the number/gender information are identified, using the context-based features of the semantic graph. The evaluation performed for the coreference resolution shows significant improvements, when compared with the word association-based bootstrapping systems.https://doi.org/10.1515/jisys-2013-0056coreference resolutionbootstrappingsemantic graphsuniversal networking language (unl)2010 mathematics subject classification: 68 computer science, 68t50 natural language processing |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Balaji J. Geetha T.V. Ranjani P. |
spellingShingle |
Balaji J. Geetha T.V. Ranjani P. Graph-Based Bootstrapping for Coreference Resolution Journal of Intelligent Systems coreference resolution bootstrapping semantic graphs universal networking language (unl) 2010 mathematics subject classification: 68 computer science, 68t50 natural language processing |
author_facet |
Balaji J. Geetha T.V. Ranjani P. |
author_sort |
Balaji J. |
title |
Graph-Based Bootstrapping for Coreference Resolution |
title_short |
Graph-Based Bootstrapping for Coreference Resolution |
title_full |
Graph-Based Bootstrapping for Coreference Resolution |
title_fullStr |
Graph-Based Bootstrapping for Coreference Resolution |
title_full_unstemmed |
Graph-Based Bootstrapping for Coreference Resolution |
title_sort |
graph-based bootstrapping for coreference resolution |
publisher |
De Gruyter |
series |
Journal of Intelligent Systems |
issn |
0334-1860 2191-026X |
publishDate |
2014-09-01 |
description |
Coreference resolution is a challenging natural language processing task, and it is difficult to identify the correct mentions of an entity that can be any noun or noun phrase. In this article, a semisupervised, two-stage pattern-based bootstrapping approach is proposed for the coreference resolution task. During Stage 1, the possible mentions are identified using word-based features, and during Stage 2, the correct mentions are identified by filtering the non-coreferents of an entity using statistical measures and graph-based features. Whereas the existing approaches use morphosyntactic and number/gender agreement features, the proposed approach uses semantic graph-based context-level semantics and nested noun phrases in the correct mentions identification. Moreover, mentions without the number/gender information are identified, using the context-based features of the semantic graph. The evaluation performed for the coreference resolution shows significant improvements, when compared with the word association-based bootstrapping systems. |
topic |
coreference resolution bootstrapping semantic graphs universal networking language (unl) 2010 mathematics subject classification: 68 computer science, 68t50 natural language processing |
url |
https://doi.org/10.1515/jisys-2013-0056 |
work_keys_str_mv |
AT balajij graphbasedbootstrappingforcoreferenceresolution AT geethatv graphbasedbootstrappingforcoreferenceresolution AT ranjanip graphbasedbootstrappingforcoreferenceresolution |
_version_ |
1717768090900496384 |