Machine Translation

, 25:179 | Cite as

The CMU-EBMT machine translation system

Article

Abstract

This paper presents an in-depth description of the features of the open-source CMU-EBMT example-based machine translation system. CMU-EBMT is a complete end-to-end system including lexicon induction, word and phrase alignment, corpus indexing and lookup, language model, decoder, and parameter tuning components. While it does not require them, it can take advantage of external alignment information and other annotations provided by GIZA++ and other systems. To illustrate a recent addition to CMU-EBMT, experiments are presented which show an improvement of 0.16 BLEU points (0.9% relative) on a cross-validated small-data English–Haitian translation task when using a new set of fine-grained log-linear feature values representing language model match lengths in addition to language model probabilities.

Keywords

Open source software Example-based machine translation Parameter tuning 

References

  1. Al-Onaizan Y, Curin J, Jahr M, Knight K, Lafferty J, Melamed I, Och FJ, Purdy D, Smith NA, Yarowsky D (1999) Statistical machine translation: final report. In: Proceedings of the summer workshop on language engineering. John Hopkins University Center for Language and Speech ProcessingGoogle Scholar
  2. Bertoldi N, Haddow B, Fouet JB (2009) Improved minimum error rate training in Moses. Prague Bull Math Linguist, pp 1–11Google Scholar
  3. Brants T, Franz A (2006) Web 1T 5-gram Version 1Google Scholar
  4. Brown RD (1996) Example-based machine translation in the Pangloss system. In: Proceedings of the sixteenth international conference on computational linguistics, Copenhagen, Denmark, pp 169–174. http://www.aclweb.org/anthology/C/C96/C96-1030.pdf
  5. Brown RD (1997) Automated dictionary extraction for “knowledge-free” example-based translation. In: Proceedings of the seventh international conference on theoretical and methodological issues in machine translation (TMI-97), Santa Fe, New Mexico, pp 111–118. http://www.cs.cmu.edu/~ralf/papers.html
  6. Brown RD (2000) Automated generalization of translation examples. In: Proceedings of the eighteenth international conference on computational linguistics (COLING-2000), pp 125–131.http://www.aclweb.org/anthology/C00-1019
  7. Brown RD (2001) Transfer-rule induction for example-based translation. In: Proceedings of the workshop on example-based machine translation. http://www.cs.-cmu.edu~ralf/papers.html
  8. Brown RD (2003) Clustered transfer rule induction for example-based translation. In: Recent advances in example-based machine translation, text, speech and language technology, chap. 10. Kluwer Academic Publishers, Dordrecht, pp 287–306Google Scholar
  9. Brown RD (2004) A modified Burrows–Wheeler transform for highly-scalable example-based translation. In: Machine translation: from real users to research, Proceedings of the 6th conference of the Association for Machine Translation in the Americas (AMTA-2004), Lecture Notes in Artificial Intelligence, vol 3265. Springer Verlag, pp 27–36. http://www.cs.cmu.edu/~ralf/papers.html
  10. Brown RD (2005) Context-sensitive retrieval for example-based machine translation. In: Proceedings of workshop: example-based machine translation, the tenth machine translation summit, pp 12–16. http://www.cs.cmu.edu/~ralf/papers.html
  11. Brown RD (2008) Exploiting document-level context for data-driven machine translation. In: Proceedings of the eighth conference of the Association for Machine Translation in the Americas (AMTA-2008). http://www.amtaweb.org/papers/-2.02_Brown.pdf
  12. Brown RD (2010) Taming structured perceptrons on wild feature vectors. In: Proceedings of the joint fifth workshop on statistical machine translation and metrics MATR. Association for Computational Linguistics, Uppsala, Sweden, pp 384–391. http://www.aclweb.org/anthology/W10-1758
  13. Brown R, Frederking R (1995) Applying statistical English language modeling to symbolic machine translation. In: Proceedings of the sixth international conference on theoretical and methodological issues in machine translation (TMI-95), pp 221–239Google Scholar
  14. Brown RD, Hutchinson R, Bennett PN, Carbonell JG, Jansen P (2003) Reducing boundary friction using translation-fragment overlap. In: Proceedings of the ninth machine translation summit, pp 24–31. http://www.cs.cmu.edu~ralf/papers.html
  15. Burrows M, Wheeler D (1994) A block-sorting lossless data compression algorithm. Tech. Rep. 124, Digital Equipment CorporationGoogle Scholar
  16. Carnegie Mellon University: public release of Haitian-Creole language data (2010). http://www.speech.cs.cmu.edu/haitian/text
  17. Frederking R (1994) Statistical language models for symbolic MT. In: Language engineering on the information highway workshop, Santorini, GreeceGoogle Scholar
  18. Frederking R, Nirenburg S (1994) Three heads are better than one. In: Proceedings of the fourth conference on applied natural language processing (ANLP-94), Stuttgart, GermanyGoogle Scholar
  19. Frederking R, Nirenburg S, Farwell D, Helmreich S, Hovy E, Knight K, Beale S, Domashnev C, Attardo D, Grannes D, Brown R (1994) Integrating translations from multiple sources within the Pangloss mark III machine translation. In: Proceedings of the first conference of the Association for Machine Translation in the Americas. Association for Machine Translation in the Americas, Columbia, Maryland, pp 73–80Google Scholar
  20. Gangadharaiah R, Brown R, Carbonell J (2006) Spectral clustering for example based machine translation. In: Proceedings of the human language technology conference of the NAACL, companion volume: short papers. Association for Computational Linguistics, pp 41–44. http://www.aclweb.org/anthology/N06-2011
  21. Gangadharaiah R, Brown RD, Carbonell JG (2010) Monolingual distributional profiles for word substitution in machine translation. In: Proceedings of the 23rd international conference on computation linguistics (COLING-2010). http://www.cs.cmu.edu/~rgangadh/rashmi_coling10.pdf
  22. Gimpel K, Smith NA (2008) Rich source-side context for statistical machine translation. In: Proceedings of the third workshop on statistical machine translation, pp 9–17Google Scholar
  23. Graff D, Kong J, Chen K, Maeda K (2007) English gigaword, 3rd edn. http://www.ldc.upenn.edu/Catalog/CatalogEntry.jsp?catalogId=LDC2007T07
  24. Hutchinson R, Bennett PN, Carbonell J, Jansen P, Brown R (2003) Maximal lattice overlap in example-based machine translation. Tech. Rep. CMU-CS-03-138. Computer Science Department, Carnegie Mellon UniversityGoogle Scholar
  25. Kim JD, Brown RD, Jansen PJ, Carbonell JG (2005) Symmetric probabilistic alignment for example-based translation. In: Proceedings of the tenth workshop of the European Assocation for Machine Translation (EAMT-05)Google Scholar
  26. Kim JD, Brown RD, Carbonell JG (2010) Chunk-Based EBMT. In: Proceedings of the 14th workshop of the European Association for Machine Translation (EAMT-2010)Google Scholar
  27. Koehn P (2004) Pharaoh: a beam search decoder for phrase-based statistical machine translation. In: Machine translation: from real users to research, proceedings of the 6th conference of the Association for Machine Translation in the Americas (AMTA-2004), Lecture Notes in Artificial Intelligence, vol 3265. Springer VerlagGoogle Scholar
  28. Koehn P, Hoang H, Birch A, Callison-Burch C, Federico M, Bertoldi N, Cowan B, Shen W, Moran C, Zens R, Dyer C, Bojar O, Constantin A, Herbst E (2007) Moses: open source toolkit for statistical machine translation. In: Proceedings of the 45th annual meeting of the Association for Computational Linguistics (ACL 2007), pp 177–180. (Demonstration session). http://www.aclweb.org/anthology/P07-2045.
  29. Lin CY, Och FJ (2004) Automatic evaluation of machine translation quality using longest common subsequence and skip-bigram statistics. In: Proceedings of the 42nd meeting of the Association for Computational Linguistics (ACL’04), main volume, Barcelona, Spain, pp 605–612. doi:10.3115/1218955.1219032. http://www.aclweb.org/anthology/P04-1077
  30. Lopez A (2007) Hierarchical phrase-based translation with suffix arrays. In: Proceedings of the 2007 joint conference on empirical methods in natural language processing and computational natural language learning, pp 976–985. http://www.aclweb.org/anthology/D/D07/D07-1104.pdf
  31. Melamed ID (1997) A word-to-word model of translational equivalence. In: Proceedings of the 35th annual meeting of the Association for Computational Linguistics (ACL’97), pp 490–497. doi:10.3115/976909.979680. http://www.aclweb.org/anthology/P97-1063
  32. Nagao M (1984) A framework of a mechanical translation between Japanese and English by analogy principle. In: Elithorn A, Banerji R (eds) Artificial and human intelligence. North-Holland, pp 173–180Google Scholar
  33. Och FJ (2003) Minimum error rate training in statistical machine translation. In: Proceedings of the 41st meeting of the Association for Computational Linguistics (ACL-2003). Association for Computational Linguistics, Sapporo, Japan, pp 160–167. doi:10.3115/1075096.1075117. http://www.aclweb.org/anthology/P03-1021
  34. Papineni K, Roukos S, Ward T, Zhu WJ (2002) BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the Association for Computational Linguistics. Association for Computational Linguistics. doi:10.3115/1073083.1073135. http://www.aclweb.org/anthology/P02-1040
  35. Phillips AB (2007) Sub-phrasal matching and structural templates in example-based MT. In: Proceedings of the 11th conference on theoretical and methodological issues in machine translation (TMI-07). http://www.dustoftheground.net/techne-/research/publications.php
  36. Phillips AB (2010) The Cunei machine translation platform for WMT ’10. In: Proceedings of the joint fifth workshop on statistical machine translation and metrics, MATR. Association for Computational Linguistics, Uppsala, Sweden, pp 149–154. http://www.aclweb.org/anthology/W10-1721
  37. Phillips AB (2011) Personal communicationGoogle Scholar
  38. Somers H (1999) Example-based machine translation. Mach Transl 14(2): 113–158MathSciNetCrossRefGoogle Scholar
  39. Stolcke A (2002) Srilm—an extensible language modeling toolkit. In: Proceedings of the 7th international conference on spoken language processing, pp 901–904Google Scholar
  40. Vogel S (2005) PESA: phrase pair extraction as sentence splitting. In: Proceedings of the tenth machine translation summit (MT Summit X)Google Scholar

Copyright information

© Springer Science+Business Media B.V. 2011

Authors and Affiliations

  1. 1.Carnegie Mellon University Language Technologies InstitutePittsburghUSA

Personalised recommendations