Discriminative Phrase-Based Models for Arabic Machine Translation

Abstract

A design for an Arabic-to-English translation system is presented. The core of the system implements a standard phrase-based statistical machine translation architecture, but it is extended by incorporating a local discriminative phrase selection model to address the semantic ambiguity of Arabic. Local classifiers are trained using linguistic information and context to translate a phrase, and this significantly increases the accuracy in phrase selection with respect to the most frequent translation traditionally considered. These classifiers are integrated into the translation system so that the global task gets benefits from the discriminative learning. As a result, we obtain significant improvements in the full translation task at the lexical, syntactic, and semantic levels as measured by an heterogeneous set of automatic evaluation metrics.

References

1. Bangalore, S., Haffner, P., and Kanthak, S. 2007. Statistical machine translation through global lexical selection and sentence reconstruction. In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics (ACL’07). 152--159.
2. Bishop, C. M. 1995. 6.4: Modeling conditional distributions. In Neural Networks for Pattern Recognition. Oxford University Press, 215.
3. Brown, P. F., Cocke, J., Pietra, S. A. D., Pietra, V. J. D., Jelinek, F., Lafferty, J. D., Mercer, R. L., and Roossin, P. S. 1990. A statistical approach to machine translation. Comput. Linguist. 16, 2, 79--85.
4. Brown, P. F., Pietra, V. J. D., Pietra, S. A. D., and Mercer, R. L. 1993. The mathematics of statistical machine translation: Parameter estimation. Comput. Linguist. 19, 2, 263--311.
5. Carpuat, M. and Wu, D. 2005. Evaluating the word sense disambiguation performance of statistical machine translation. In Proceedings of the International Joint Conference on Natural Language Processing (IJCNLP’05).
6. Carpuat, M. and Wu, D. 2007. How phrase sense disambiguation outperforms word sense disambiguation for statistical machine translation. In Proceedings of the 11th Conference on Theoretical and Methodological Issues in Machine Translation (TMI’07).
7. Chiang, D. 2005. A hierarchical phrase-based model for statistical machine translation. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL’05). Association for Computational Linguistics, 263--270.
8. Diab, M., Hacioglu, K., and Jurafsky, D. 2004. Automatic tagging of Arabic text: From raw text to base phrase chunks. In Proceedings of the 5th Meeting of the North American Chapter of the Association for Computational Linguistics/Human Language Technologies Conference (HLT-NAACL’04).
9. El Isbihani, A., Khadivi, S., Bender, O., and Ney, H. 2006. Morpho-syntactic Arabic preprocessing for Arabic to English statistical machine translation. In Proceedings of the Human Language Technology Conference/North American Chapter of the Association for Computational Linguistics Annual Meeting, Workshop on Statistical Machine Translation. Association for Computational Linguistics (HLT-NAACL’06). 15--22.
10. Fellbaum, C., Alkhalifa, M., Black, W. J., Elkateb, S., Pease, A., Rodríguez, H., and Vossen, P. 2006. Introducing the Arabic wordnet project. In Proceedings of the 3rd Global Wordnet Conference (GWA’06).
11. Giménez, J. 2007. IQMT v 2.1. Technical Manual (LSI-07-29-R). Tech. rep., TALP Research Center. LSI Department. http://www.lsi.upc.edu/~nlp/IQMT/IQMT.v2.1.pdf.
12. Giménez, J. and Amigó, E. 2006. IQMT: A framework for automatic machine translation evaluation. In Proceedings of the 5th Annual Conference on Language Resources and Evaluation (LREC’06). 685--690.
13. Giménez, J. and Màrquez, L. 2008. Discriminative phrase selection for SMT. In Proceedings of the Conference on Advances in Neutral Information Processing Systems (NIPS’08). 205--236.
14. Joachims, T. 1999. Making large-scale support vector machine learning practical, 169--184.
15. Koehn, P. 2004. Statistical significance tests for machine translation evaluation. In Proceedings of the Joint Meeting of the Conference on Empirical Methods in Natural Language Processing (EMNLP’04).
16. Koehn, P., Hoang, H., Mayne, A. B., Callison-Burch, C., Federico, M., Bertoldi, N., Cowan, B., Shen, W., Moran, C., Zens, R., Dyer, C., Bojar, O., Constantin, A., and Herbst, E. 2007. Moses: Open source toolkit for statistical machine translation. In Proceedings of the Annual Meeting of the Association for Computation Linguistics (ACL’07). 177--180.
17. Koehn, P., Och, F. J., and Marcu, D. 2003. Statistical phrase-based translation. In Proceedings of the Human Language Technology and North American Association for Computational Linguistics Conference (HLT/NAACL’03).
18. Koehn, P., Shen, W., Federico, M., Bertoldi, N., Callison-Burch, C., Cowan, B., Dyer, C., Hoang, H., Bojar, O., Zens, R., Constantin, A., Herbst, E., and Moran, C. 2006. Open source toolkit for statistical machine translation. Tech. rep., Johns Hopkins University Summer Workshop. http://www.statmt.org/jhuws/.
19. Kudo, T. and Matsumoto, Y. 2003. Fast methods for kernelbased text analysis. In Proceedings of the Association for Computational Linguistics (ACL’03).
20. Och, F. J. 2003. Minimum error rate training in statistical machine translation. In Proceedings of the Association for Computational Linguistics (ACL’03).
21. Och, F. J. and Ney, H. 2002. Discriminative training and maximum entropy models for statistical machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL’02). 295--302.
22. Och, F. J. and Ney, H. 2003. A systematic comparison of various statistical alignment models. Comput. Linguist. 29, 1, 19--51.
23. Och, F. J. and Ney, H. 2004. The alignment template approach to statistical machine translation. Comput. Linguist. 30, 4, 417--449.
24. Papineni, K., Roukos, S., Ward, T., and Zhu, W.-J. 2002. Bleu: A method for automatic evaluation of machine translation. In Proceedings of the Association of Computational Linguistics (ACL’02). 311--318.
25. Specia, L., Sankaran, B., and das Graças Volpe Nunes, M. 2008. N-best reranking for the efficient integration of word sense disambiguation and statistical Machine translation. In Proceedings of the Computational Linguistics and Intelligent Text Processing. Lecture Notes in Computer Science, vol. 4919, Springer, Berlin, 399--410.
26. Stolcke, A. 2002. SRILM -- An extensible language modeling toolkit. In Proceedings of the International Conference on Spoken Language Processing (ICSLP’02).
27. Stroppa, N., van den Bosch, A., and Way, A. 2007. Exploiting source similarity for SMT using context-informed features. In Proceedings of the 11th Conference on Theoretical and Methodological Issues in Machine Translation (TMI’07). 231--240.
28. Vickrey, D., Biewald, L., Teyssier, M., and Koller, D. 2005. Word-sense disambiguation for machine translation. In Proceedings of the Joint Conference on Human Language Technology and Empirical Methods in Natural Language Processing (HLT-EMNLP’05).
29. Yamada, K. and Knight, K. 2001. A syntax-based statistical translation model. In Proceedings of the Association of Computer Linguistics (ACL’01). 523--530.

Index Terms

• Computing methodologies

  • Artificial intelligence

    • Natural language processing

      • Machine translation

  • Machine learning