Knowledge-rich Word Sense Disambiguation Rivaling Supervised Systems
S. Ponzetto, and R. Navigli. Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, page 1522--1531. Stroudsburg, PA, USA, Association for Computational Linguistics, (2010)
Abstract
One of the main obstacles to high-performance Word Sense Disambiguation (WSD) is the knowledge acquisition bottleneck. In this paper, we present a methodology to automatically extend WordNet with large amounts of semantic relations from an encyclopedic resource, namely Wikipedia. We show that, when provided with a vast amount of high-quality semantic relations, simple knowledge-lean disambiguation algorithms compete with state-of-the-art supervised WSD systems in a coarse-grained all-words setting and outperform them on gold-standard domain-specific datasets.
Description
Knowledge-rich Word Sense Disambiguation rivaling supervised systems
%0 Conference Paper
%1 Ponzetto:2010:KWS:1858681.1858835
%A Ponzetto, Simone Paolo
%A Navigli, Roberto
%B Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
%C Stroudsburg, PA, USA
%D 2010
%I Association for Computational Linguistics
%K babelnet disambiguation namedentity phdproposal wordsense
%P 1522--1531
%T Knowledge-rich Word Sense Disambiguation Rivaling Supervised Systems
%U http://dl.acm.org/citation.cfm?id=1858681.1858835
%X One of the main obstacles to high-performance Word Sense Disambiguation (WSD) is the knowledge acquisition bottleneck. In this paper, we present a methodology to automatically extend WordNet with large amounts of semantic relations from an encyclopedic resource, namely Wikipedia. We show that, when provided with a vast amount of high-quality semantic relations, simple knowledge-lean disambiguation algorithms compete with state-of-the-art supervised WSD systems in a coarse-grained all-words setting and outperform them on gold-standard domain-specific datasets.
@inproceedings{Ponzetto:2010:KWS:1858681.1858835,
abstract = {One of the main obstacles to high-performance Word Sense Disambiguation (WSD) is the knowledge acquisition bottleneck. In this paper, we present a methodology to automatically extend WordNet with large amounts of semantic relations from an encyclopedic resource, namely Wikipedia. We show that, when provided with a vast amount of high-quality semantic relations, simple knowledge-lean disambiguation algorithms compete with state-of-the-art supervised WSD systems in a coarse-grained all-words setting and outperform them on gold-standard domain-specific datasets.},
acmid = {1858835},
added-at = {2014-12-30T00:54:31.000+0100},
address = {Stroudsburg, PA, USA},
author = {Ponzetto, Simone Paolo and Navigli, Roberto},
biburl = {https://www.bibsonomy.org/bibtex/2862a90089a8946b5d0cbb2685fd616e1/asmelash},
booktitle = {Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics},
description = {Knowledge-rich Word Sense Disambiguation rivaling supervised systems},
interhash = {ebcc1f612c8fb40374d69c76516119a4},
intrahash = {862a90089a8946b5d0cbb2685fd616e1},
keywords = {babelnet disambiguation namedentity phdproposal wordsense},
location = {Uppsala, Sweden},
numpages = {10},
pages = {1522--1531},
publisher = {Association for Computational Linguistics},
series = {ACL '10},
timestamp = {2014-12-30T00:54:45.000+0100},
title = {Knowledge-rich Word Sense Disambiguation Rivaling Supervised Systems},
url = {http://dl.acm.org/citation.cfm?id=1858681.1858835},
year = 2010
}