Speeding Up Target-Language Driven Part-of-Speech Tagger Training for Machine Translation
When training hidden-Markov-model-based part-of-speech (PoS) taggers involved in machine translation systems in an unsupervised manner the use of target-language information has proven to give better results than the standard Baum-Welch algorithm. The target-language-driven training algorithm proceeds by translating every possible PoS tag sequence resulting from the disambiguation of the words in each source-language text segment into the target language, and using a target-language model to estimate the likelihood of the translation of each possible disambiguation. The main disadvantage of this method is that the number of translations to perform grows exponentially with segment length, translation being the most time-consuming task. In this paper, we present a method that uses a priori knowledge obtained in an unsupervised manner to prune unlikely disambiguations in each text segment, so that the number of translations to be performed during training is reduced. The experimental results show that this new pruning method drastically reduces the amount of translations done during training (and, consequently, the time complexity of the algorithm) without degrading the tagging accuracy achieved.
Unable to display preview. Download preview PDF.
- 2.Baum, L.E.: An inequality and associated maximization technique in statistical estimation of probabilistic functions of a Markov process. Inequalities 3, 1–8 (1972)Google Scholar
- 3.Sánchez-Martínez, F., Pérez-Ortiz, J.A., Forcada, M.L.: Exploring the use of target-language information to train the part-of-speech tagger of machine translation systems. In: Vicedo, J.L., Martínez-Barco, P., Muńoz, R., Saiz Noeda, M. (eds.) EsTAL 2004. LNCS (LNAI), vol. 3230, pp. 137–148. Springer, Heidelberg (2004)CrossRefGoogle Scholar
- 4.Corbí-Bellot, A.M., Forcada, M.L., Ortiz-Rojas, S., Pérez-Ortiz, J.A., Ramírez-Sánchez, G., Sánchez-Martínez, F., Alegria, I., Mayor, A., Sarasola, K.: An open-source shallow-transfer machine translation engine for the Romance languages of Spain. In: Proceedings of the 10th European Associtation for Machine Translation Conference, Budapest, Hungary, pp. 79–86 (2005)Google Scholar
- 5.Cutting, D., Kupiec, J., Pedersen, J., Sibun, P.: A practical part-of-speech tagger. In: Third Conference on Applied Natural Language Processing. Association for Computational Linguistics. Proceedings of the Conference, Trento, Italia, pp. 133–140 (1992)Google Scholar
- 8.Armentano-Oller, C., Carrasco, R.C., CorbÍ-Bellot, A.M., Forcada, M.L., Ginestí-Rosell, M., Ortiz-Rojas, S., Pérez-Ortiz, J.A., Ramírez-Sánchez, G., Sánchez-Martínez, F., Scalco, M.A.: Open-source Portuguese-Spanish machine translation. In: Vieira, R., Quaresma, P., Nunes, M.d.G.V., Mamede, N.J., Oliveira, C., Dias, M.C. (eds.) PROPOR 2006. LNCS (LNAI), vol. 3960, pp. 50–59. Springer, Heidelberg (2006)CrossRefGoogle Scholar