The need for application-dependent WSD strategies: a case study in MT

Authors:
Lucia Specia;Gabriela Castelo Branco Ribeiro;Maria das GraçasVolpe Nunes;Mark Stevenson
Affiliations:
ICMC – University of São Paulo, São Carlos, Brazil;DL – Pontificial Catholic University, Rio de Janeiro, RJ, Brazil;ICMC – University of São Paulo, São Carlos, Brazil;Regent Court, DCS – University of Sheffield, Sheffield, UK
Venue:
PROPOR'06 Proceedings of the 7th international conference on Computational Processing of the Portuguese Language
Year:
2006

Citing 6
Cited 0

Word sense disambiguation using a second language monolingual corpus

Computational Linguistics
Assessing agreement on classification tasks: the kappa statistic

Computational Linguistics
The grammar of sense: Using part-of-speech tags as a first step in semantic disambiguation

Natural Language Engineering
An unsupervised method for word sense tagging using parallel corpora

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Exploiting parallel texts for word sense disambiguation: an empirical study

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Evaluating cross-language annotation transfer in the MultiSemCor corpus

COLING '04 Proceedings of the 20th international conference on Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

It is generally agreed that the ultimate goal of research into Word Sense Disambiguation (WSD) is to provide a technology which can benefit applications; however, most of the work in this area has focused on the development of application-independent models. Taking Machine Translation as the application, we argue that this strategy is not appropriate, since many aspects of algorithm design, such as the sense repository, depend on the application. We present evidence for this by investigating the disambiguation of nine verbs in English-Portuguese translations.