The Need for Application-Dependent WSD Strategies: A Case Study in MT
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.
Unable to display preview. Download preview PDF.
- 1.Bentivogli, L., Forner, P., Pianta, E.: Evaluating Cross-Language Annotation Transfer in the MultiSemCor Corpus. In: COLING 2004, Geneva, pp. 364–370 (2004)Google Scholar
- 2.Carletta, J.: Assessing agreement on classification tasks: the kappa statistic. Computational Linguistics 22(2), 249–254 (1996)Google Scholar
- 3.Dagan, I., Itai, A.: Word Sense Disambiguation Using a Second Language Monolingual Corpus. Computational Linguistics 20, 563–596 (1994)Google Scholar
- 4.Diab, M., Resnik, P.: An Unsupervised Method for Word Sense Tagging using Parallel Corpora. In: 40th Anniversary Meeting of the ACL, Philadelphia (2002)Google Scholar
- 5.Ide, N.: Parallel Translations as Sense Discriminators. In: SIGLEX 1999 Workshop: Standardizing Lexical Resources, Maryland, pp. 52–61 (1999)Google Scholar
- 6.Miháltz, M.: Towards A Hybrid Approach To Word-Sense Disambiguation in Machine Translation. In: Workshop Modern Approaches in Translation Technologies - RANLP 2005, Borovets (2005)Google Scholar
- 8.Ng, H.T., Wang, B., Chan, Y.S.: Exploiting Parallel Texts for Word Sense Disambiguation: An Empirical Study. In: 41st Annual Meeting of the ACL, Sapporo, 455–462 (2003)Google Scholar