Machine Translation

, Volume 24, Issue 2, pp 123–140 | Cite as

Exploiting syntactic relationships in a phrase-based decoder: an exploration

Article

Abstract

Phrase-based decoding is conceptually simple and straightforward to implement, at the cost of drastically oversimplified reordering models. Syntactically aware models make it possible to capture linguistically relevant relationships in order to improve word order, but they can be more complex to implement and optimise. In this paper, we explore a new middle ground between phrase-based and syntactically informed statistical MT, in the form of a model that supplements conventional, non-hierarchical phrase-based techniques with linguistically informed reordering based on syntactic dependency trees. The key idea is to exploit linguistically-informed hierchical structures only for those dependencies that cannot be captured within a single flat phrase. For very local dependencies we leverage the success of conventional phrase-based approaches, which provide a sequence of target-language words appropriately ordered and ready-made with any agreement morphology. Working with dependency trees rather than constituency trees allows us to take advantage of the flexibility of phrase-based systems to treat non-constituent fragments as phrases. We do impose a requirement—that the fragment be a novel sort of “dependency constituent”—on what can be translated as a phrase, but this is much weaker than the requirement that phrases be traditional linguistic constituents, which has often proven too restrictive in MT systems.

Keywords

Statistical MT Phrase-based translation Syntax Reordering 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Brown PF, Cocke J, Pietra SAD, Pietra VJD, Jelinek F, Lafferty JD, Mercer RL, Roossin PS (1990) A statistical approach to machine translation. Comput Ling 16(2): 79–85Google Scholar
  2. Chiang D (2005) A hierarchical phrase-based model for statistical machine translation. In: Proceedings of ACL, pp 263–270Google Scholar
  3. Chiang D, Marton Y, Resnik P (2008) Online large-margin training of syntactic and structural translation features. In: Proceedings of EMNLP, pp 224–233Google Scholar
  4. Cmejrek M, Cuřín J, Havelka J (2004) Prague Czech-English dependency treebank: any hopes for a common annotation scheme? In: Proceedings of HLT/NAACL 2004 workshop: frontiers in corpus annotation, pp 47–54Google Scholar
  5. Collins M, Koehn P, Kučerová I (2005) Clause restructuring for statistical machine translation. In: Proceedings of ACL, pp 531–540Google Scholar
  6. Dyer C, Resnik P (2010) Forest translation. In: Proceedings of NAACL-HLTGoogle Scholar
  7. Fox HJ (2002) Phrasal cohesion and statistical machine translation. In: Proceedings of EMNLP, pp 304–311Google Scholar
  8. Galley M, Manning CD (2008) A simple and effective hierarchical phrase reordering model. In: Proceedings of EMNLP, pp 848–856Google Scholar
  9. Galley M, Hopkins M, Knight K, Marcu D (2004) What’s in a translation rule? In: Proceedings of HLT-NAACL, pp 273–280Google Scholar
  10. Gildea D (2003) Loosely tree-based alignment for machine translation. In: Proceedings of ACL, pp 80–87Google Scholar
  11. Hunter T, Resnik P (2009) Extending phrase-based decoding with a dependency-based reordering model. Technical Report UMIACS-TR-2009-15, LAMP-TR-152. Available at http://hdl.handle.net/1903/9782
  12. Hwa R, Resnik P, Weinberg A, Kolak O (2002) Evaluating translation correspondence using annotation projection. In: Proceedings of ACL, pp 392–399Google Scholar
  13. Kahn JG, Snover M, Ostendorf M (2009) Expected dependency pair match: predicting translation quality with expected syntactic structure. Mach Transl. Published online 31 October 2009Google Scholar
  14. Koehn P, Och FJ, Marcu D (2003) Statistical phrase based translation. In: Proceedings of HLT-NAACL, pp 127–133Google Scholar
  15. Lee Y-S, Roukos S, Al-Onaizan Y, Papieni K (2006) IBM spoken language translation system. In: Proceedings of TC-STAR Workshop, pp 13–18Google Scholar
  16. Marton Y, Resnik P (2008) Soft syntactic constraints for hierarchical phrase-based translation. In: Proceedings of ACL, pp 1003–1011Google Scholar
  17. Och F (2003) Minimum error rate training for statistical machine translation. In: Proceedings of ACL, pp 160–167Google Scholar
  18. Och FJ, Tillman C, Ney H (1999) Improved alignment models for statistical machine translation. In: Proceedings of the joint conference of empirical methods in natural language processing and very large corpora, pp 20–28Google Scholar
  19. Quirk C, Menezes A, Cherry C (2005) Dependency tree translation: syntactically informed phrasal SMT. In: Proceedings of ACL, pp 271–279Google Scholar
  20. Shen L, Xu J, Weischedel R (2008) A new string-to-dependency machine translation algorithm with a target dependency language model. In: Proceedings of ACL, pp 577–585Google Scholar
  21. Shen L, Xu J, Zhang B, Weischedel SMR (2009) Effective use of linguistic and contextual information for statistical machine translation. In: Proceedings of EMNLP, pp 72–80Google Scholar
  22. Tromble R, Eisner J (2009) Learning linear ordering problems for better translation. In: Proceedings of EMNLP, pp 1007–1016Google Scholar
  23. Wu D, Wong H (1998) Machine translation with a stochastic grammatical channel. In: Proceedings of ACL-COLING, pp 1408–1415Google Scholar
  24. Xia F, McCord M (2004) Improving a statistical MT system with automatically learned rewrite patterns. In: Proceedings of COLING, pp 508–514Google Scholar
  25. Yamada K, Knight K (2001) A syntax-based statistical translation model. In: Proceedings of ACL, pp 523–530Google Scholar

Copyright information

© Springer Science+Business Media B.V. 2010

Authors and Affiliations

  1. 1.University of MarylandCollege ParkUSA

Personalised recommendations