UoY: Graphs of unambiguous vertices for word sense induction and disambiguation
I. Korkontzelos, and S. Manandhar. Proceedings of the 5th International Workshop on Semantic Evaluation, page 355--358. Stroudsburg, PA, USA, Association for Computational Linguistics, (2010)
Abstract
This paper presents an unsupervised graph-based method for automatic word sense induction and disambiguation. The innovative part of our method is the assignment of either a word or a word pair to each vertex of the constructed graph. Word senses are induced by clustering the constructed graph. In the disambiguation stage, each induced cluster is scored according to the number of its vertices found in the context of the target word. Our system participated in SemEval-2010 word sense induction and disambiguation task.
%0 Conference Paper
%1 Korkontzelos:2010:UGU:1859664.1859743
%A Korkontzelos, Ioannis
%A Manandhar, Suresh
%B Proceedings of the 5th International Workshop on Semantic Evaluation
%C Stroudsburg, PA, USA
%D 2010
%I Association for Computational Linguistics
%K 2010 based graph semeval uoy wsi
%P 355--358
%T UoY: Graphs of unambiguous vertices for word sense induction and disambiguation
%U http://dl.acm.org/citation.cfm?id=1859664.1859743
%X This paper presents an unsupervised graph-based method for automatic word sense induction and disambiguation. The innovative part of our method is the assignment of either a word or a word pair to each vertex of the constructed graph. Word senses are induced by clustering the constructed graph. In the disambiguation stage, each induced cluster is scored according to the number of its vertices found in the context of the target word. Our system participated in SemEval-2010 word sense induction and disambiguation task.
@inproceedings{Korkontzelos:2010:UGU:1859664.1859743,
abstract = {This paper presents an unsupervised graph-based method for automatic word sense induction and disambiguation. The innovative part of our method is the assignment of either a word or a word pair to each vertex of the constructed graph. Word senses are induced by clustering the constructed graph. In the disambiguation stage, each induced cluster is scored according to the number of its vertices found in the context of the target word. Our system participated in SemEval-2010 word sense induction and disambiguation task.},
acmid = {1859743},
added-at = {2011-09-07T13:35:02.000+0200},
address = {Stroudsburg, PA, USA},
author = {Korkontzelos, Ioannis and Manandhar, Suresh},
biburl = {https://www.bibsonomy.org/bibtex/2e8f0c0618b514b54b3c2245ae919f3d0/jil},
booktitle = {Proceedings of the 5th International Workshop on Semantic Evaluation},
interhash = {660bc2447bd2ad05b3fc248a9bf0e008},
intrahash = {e8f0c0618b514b54b3c2245ae919f3d0},
keywords = {2010 based graph semeval uoy wsi},
location = {Los Angeles, California},
numpages = {4},
pages = {355--358},
publisher = {Association for Computational Linguistics},
series = {SemEval '10},
timestamp = {2013-11-23T20:11:51.000+0100},
title = {UoY: Graphs of unambiguous vertices for word sense induction and disambiguation},
url = {http://dl.acm.org/citation.cfm?id=1859664.1859743},
year = 2010
}