Abstract
All words in every natural language are ambiguous, specially when translation is at stake. In translation tasks, there is the need for finding out adequate translations for such words in the contexts where they occur. In this article, a bilingual strategy to cluster words according to their meanings is described. A publicly available parallel corpora sentence aligned is used. Word senses are discriminated by their translations and by the words occurring in a window, both in the source and target language parallel sentences. This strategy is language independent and uses a correlation algorithm for filtering out irrelevant features. Clusters obtained were evaluated in terms of F-measure (getting an average rating of 94%) and their homogeneity and completeness was determined using V-Measure (getting an average rating of 83%). Learned clusters are then used to train a support vector machine to tag ambiguous words with their translations in the contexts where they occur. This task was also evaluated in terms of F-measure and confronted with a baseline.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Aires, J., Lopes, G.P., Gomes, L.: Phrase translation extraction from aligned parallel corpora using suffix arrays and related structures. In: Lopes, L.S., Lau, N., Mariano, P., Rocha, L.M. (eds.) EPIA 2009. LNCS (LNAI), vol. 5816, pp. 587–597. Springer, Heidelberg (2009)
Gale, W.A., Church, K.W., Yarowsky, D.: A method for disambiguating word senses in a large corpus. Computers and the Humanities 26, 415–439 (1992)
Bar-Hillel, Y.: The present status of automatic translation of languages. Advances in Computers 1, 91–163 (1960)
Li, P., Church, K.W.: A sketch algorithm for estimating two-way and multi-way associations. Computational Linguistics 33, 305–354 (2007)
Mihalcea, R., Moldovan, D.I.: A method for word sense disambiguation of unrestricted text. In: Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics on Computational Linguistics, pp. 152–158. Association for Computational Linguistics (1999)
Gamallo, P., Agustini, A., Lopes, G.P.: Clustering syntactic positions with similar semantic requirements. Computational Linguistics 31, 107–146 (2005)
Ponzetto, S.P., Navigli, R.: Knowledge-rich word sense disambiguation rivaling supervised systems. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pp. 1522–1531. Association for Computational Linguistics (2010)
Zhong, Z., Ng, H.T.: Word sense disambiguation improves information retrieval. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics. Long Papers, vol. 1, pp. 273–282. Association for Computational Linguistics (2012)
Moraliyski, R., Dias, G.: One sense per discourse for synonymy extraction. In: International Conference on Recent Advances in Natural Language Processing, RANLP 2007, vol. 2, pp. 383–387 (2008)
Bansal, M., DeNero, J., Lin, D.: Unsupervised translation sense clustering. In: Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 773–782. Association for Computational Linguistics (2012)
Apidianaki, M., He, Y., et al.: An algorithm for cross-lingual sense-clustering tested in a mt evaluation setting. In: Proceedings of the International Workshop on Spoken Language Translation, pp. 219–226 (2010)
Brown, P.F., Pietra, S.A.D., Pietra, V.J.D., Mercer, R.L.: Word-sense disambiguation using statistical methods. In: Proceedings of the 29th Annual Meeting on Association for Computational Linguistics, pp. 264–270. Association for Computational Linguistics (1991)
Diab, M.T., et al.: Word sense disambiguation within a multilingual framework (2003)
TufiŞ, D., Ion, R., Ide, N.: Fine-grained word sense disambiguation based on parallel corpora, word alignment, word clustering and aligned wordnets. In: Proceedings of the 20th International Conference on Computational Linguistics, p. 1312. Association for Computational Linguistics (2004)
Lefever, E., Hoste, V., De Cock, M.: Five languages are better than one: an attempt to bypass the data acquisition bottleneck for wsd. In: Gelbukh, A. (ed.) CICLing 2013, Part I. LNCS, vol. 7816, pp. 343–354. Springer, Heidelberg (2013)
Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The weka data mining software: an update. ACM SIGKDD Explorations Newsletter 11, 10–18 (2009)
Pelleg, D., Moore, A.W., et al.: X-means: Extending k-means with efficient estimation of the number of clusters. In: ICML, pp. 727–734 (2000)
Rosenberg, A., Hirschberg, J.: V-measure: A conditional entropy-based external cluster evaluation measure. In: EMNLP-CoNLL, vol. 7, pp. 410–420 (2007)
Rijsbergen, V. (ed.): Information Retrieval, 2nd edn. Information Retrieval Group. University of Glasgow (1979)
Chang, C.C., Lin, C.J.: Libsvm: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology (TIST) 2, 27 (2011)
Lefever, E., Hoste, V.: Semeval-2010 task 3: Cross-lingual word sense disambiguation. In: Proceedings of the 5th International Workshop on Semantic Evaluation, pp. 15–20. Association for Computational Linguistics(2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Casteleiro, J., Lopes, G.P., Silva, J. (2014). Bilingually Learning Word Senses for Translation. In: Gelbukh, A. (eds) Computational Linguistics and Intelligent Text Processing. CICLing 2014. Lecture Notes in Computer Science, vol 8404. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-54903-8_24
Download citation
DOI: https://doi.org/10.1007/978-3-642-54903-8_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-54902-1
Online ISBN: 978-3-642-54903-8
eBook Packages: Computer ScienceComputer Science (R0)