Exploiting semantic role labeling, WordNet and Wikipedia for coreference resolution
S. Ponzetto, и M. Strube. Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, стр. 192--199. Morristown, NJ, USA, Association for Computational Linguistics, (2006)
DOI: http://dx.doi.org/10.3115/1220835.1220860
Аннотация
In this paper we present an extension of a machine learning based coreference resolution system which uses features induced from different semantic knowledge sources. These features represent knowledge mined from WordNet and Wikipedia, as well as information about semantic role labels. We show that semantic features indeed improve the performance on different referring expression types such as pronouns and common nouns.
Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics
%0 Conference Paper
%1 1220860
%A Ponzetto, Simone Paolo
%A Strube, Michael
%B Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics
%C Morristown, NJ, USA
%D 2006
%I Association for Computational Linguistics
%K Wikipedia coreference semantic_web
%P 192--199
%R http://dx.doi.org/10.3115/1220835.1220860
%T Exploiting semantic role labeling, WordNet and Wikipedia for coreference resolution
%U http://portal.acm.org/citation.cfm?id=1220860
%X In this paper we present an extension of a machine learning based coreference resolution system which uses features induced from different semantic knowledge sources. These features represent knowledge mined from WordNet and Wikipedia, as well as information about semantic role labels. We show that semantic features indeed improve the performance on different referring expression types such as pronouns and common nouns.
@inproceedings{1220860,
abstract = {In this paper we present an extension of a machine learning based coreference resolution system which uses features induced from different semantic knowledge sources. These features represent knowledge mined from WordNet and Wikipedia, as well as information about semantic role labels. We show that semantic features indeed improve the performance on different referring expression types such as pronouns and common nouns.},
added-at = {2008-01-18T06:15:46.000+0100},
address = {Morristown, NJ, USA},
author = {Ponzetto, Simone Paolo and Strube, Michael},
biburl = {https://www.bibsonomy.org/bibtex/2f2a37c243216ec7906a205fd3d46bf31/pitman},
booktitle = {Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics},
doi = {http://dx.doi.org/10.3115/1220835.1220860},
interhash = {04f649208bc4ce5ac4d373702c9f6ea9},
intrahash = {f2a37c243216ec7906a205fd3d46bf31},
keywords = {Wikipedia coreference semantic_web},
location = {New York, New York},
pages = {192--199},
publisher = {Association for Computational Linguistics},
timestamp = {2008-01-18T06:15:47.000+0100},
title = {Exploiting semantic role labeling, WordNet and Wikipedia for coreference resolution},
url = {http://portal.acm.org/citation.cfm?id=1220860},
year = 2006
}