Statistical phrase-based translation

ABSTRACT

We propose a new phrase-based translation model and decoding algorithm that enables us to evaluate and compare several, previously proposed phrase-based translation models. Within our framework, we carry out a large number of experiments to understand better and explain why phrase-based models out-perform word-based models. Our empirical results, which hold for all examined language pairs, suggest that the highest levels of performance can be obtained through relatively simple means: heuristic learning of phrase translations from word-based alignments and lexical weighting of phrase translations. Surprisingly, learning phrases longer than three words and learning phrases from high-accuracy word-level alignment models does not have a strong impact on performance. Learning only syntactically motivated phrases degrades the performance of our systems.

REFERENCES

• 1: Peter F. Brown , Vincent J. Della Pietra , Stephen A. Della Pietra , Robert L. Mercer, The mathematics of statistical machine translation: parameter estimation, Computational Linguistics, v.19 n.2, June 1993
• 2: Michael Collins, Three generative, lexicalised models for statistical parsing, Proceedings of the 35th annual meeting on Association for Computational Linguistics, p.16-23, July 07-12, 1997, Madrid, Spain
• 3: Ulrich Germann , Michael Jahr , Kevin Knight , Daniel Marcu , Kenji Yamada, Fast decoding and optimal decoding for machine translation, Proceedings of the 39th Annual Meeting on Association for Computational Linguistics, p.228-235, July 06-11, 2001, Toulouse, France [doi>10.3115/1073012.1073042]
• 4: Imamura, K. (2002). Application of translation knowledge acquired by hierarchical phrase alignment for pattern-based mt. In Proceedings of TMI.
• 5: Frederick Jelinek, Statistical methods for speech recognition, MIT Press, Cambridge, MA, 1998
• 6: Daniel Marcu , William Wong, A phrase-based, joint probability model for statistical machine translation, Proceedings of the ACL-02 conference on Empirical methods in natural language processing, p.133-139, July 06, 2002 [doi>10.3115/1118693.1118711]
• 7: Franz Josef Och , Hermann Ney, Improved statistical alignment models, Proceedings of the 38th Annual Meeting on Association for Computational Linguistics, p.440-447, October 03-06, 2000, Hong Kong [doi>10.3115/1075218.1075274]
• 8: Och, F. J., Tillmann, C., and Ney, H. (1999). Improved alignment models for statistical machine translation. In Proc. of the Joint Conf. of Empirical Methods in Natural Language Processing and Very Large Corpora, pages 20--28.
• 9: Franz Josef Och , Nicola Ueffing , Hermann Ney, An efficient A* search algorithm for statistical machine translation, Proceedings of the workshop on Data-driven methods in machine translation, p.1-8, July 07-07, 2001, Toulouse, France [doi>10.3115/1118037.1118045]
• 10: Papineni, K., Roukos, S., Ward, T., and Zhu, W.-J. (2001). BLEU: a method for automatic evaluation of machine translation. Technical Report RC22176(W0109-022), IBM Research Report.
• 11: Helmut Schmid , Sabine Schulte im Walde, Robust German noun chunking with a probabilistic context-free grammar, Proceedings of the 18th conference on Computational linguistics, July 31-August 04, 2000, Saarbrücken, Germany [doi>10.3115/992730.992751]
• 12: Seymore, K. and Rosenfeld, R. (1997). Statistical language modeling using the CMU-Cambridge toolkit. In Proceedings of Eurospeech.
• 13: Dekai Wu, Stochastic inversion transduction grammars and bilingual parsing of parallel corpora, Computational Linguistics, v.23 n.3, p.377-403, September 1997
• 14: Kenji Yamada , Kevin Knight, A syntax-based statistical translation model, Proceedings of the 39th Annual Meeting on Association for Computational Linguistics, p.523-530, July 06-11, 2001, Toulouse, France [doi>10.3115/1073012.1073079]