Machine Translation

, Volume 19, Issue 3–4, pp 213–227 | Cite as

MT model space: statistical versus compositional versus example-based machine translation

Examble-Based MT

Abstract

We offer a perspective on EBMT from a statistical MT standpoint, by developing a three-dimensional MT model space based on three pairs of definitions: (1) logical versus statistical MT, (2) schema-based versus example-based MT, and (3) lexical versus compositional MT. Within this space we consider the interplay of three key ideas in the evolution of transfer, example-based, and statistical approaches to MT. We depict how all translation models face these issues in one way or another, regardless of the school of thought, and suggest where the real questions for the future may lie.

Keywords

Statistical MT Example-based MT Compositional MT 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Aha DW, Kibler D, Albert MK (1991) Instance-based learning algorithms. Mach Learn 6:37–66Google Scholar
  2. Alshawi H, Bangalore S, Douglas S (1998) Automatic acquisition of hierarchical transduction models for machine translation. In: COLING-ACL ’98: 36th annual meeting of the Association for Computational Linguistics and 17th international conference on computational linguistics, Montreal, Quebec, Canada, pp 41–47Google Scholar
  3. Alshawi H, Buchsbaum AL, Xia F (1997) A comparison of head transducers and transfer for a limited domain translation application. In: 35th Annual meeting of the Association for Computational Linguistics, Madrid, Spain, pp 360–365Google Scholar
  4. Alshawi H, Douglas S, Bangalore S (2000) Learning dependency translation models as collections of finite-state head transducers. Comput Ling 26:45–60CrossRefGoogle Scholar
  5. American Heritage (2000) The American heritage dictionary of the English language, 4th edn. Houghton Mifflin, Boston, MAGoogle Scholar
  6. Andriamanankasina T, Araki K, Tochinai K (2003) EBMT of POS-tagged sentences by recursive division via inductive learning. In: Carl and Way (2003), pp 225–252Google Scholar
  7. Angluin D (1980) Inductive inference of formal languages from positive data. Inform Control 45:117–135CrossRefGoogle Scholar
  8. Aramaki E, Kurohashi S, Kashioka H, Kato N (2005) Probabilistic model for example-based machine translation. In: MT Summit X: The tenth machine translation summit, Phuket, Thailand, pp 219–226Google Scholar
  9. Bond F, Shirai S (2003) A hybrid rule and example-based method for machine translation. In: Carl and Way (2003), pp 211–224Google Scholar
  10. Brown PE, Cocke J, Della Pietra SA, Della Pietra VJ, Jelinek F, Lafferty JD, Mercer RL, Roossin PS (1990) A statistical approach to machine translation. Comput Ling 16:79–85; repr. in Nirenburg et al. (2003), pp 355–362Google Scholar
  11. Brown PE, Della Pietra VJ, Della Pietra SA, Mercer RL (1993) The mathematics of statistical machine translation: Parameter estimation. Comput Ling 19:263–311Google Scholar
  12. Brown RD (1999) Adding linguistic knowledge to a lexical example-based translation system. In: Proceedings of the eighth international conference on theoretical and methodological issues in machine translation (TMI-99), Chester, England, pp 22–32Google Scholar
  13. Brown RD (2003) Clustered transfer rule induction for example-based translation. In: Carl and Way (2003), pp 287–305Google Scholar
  14. Carl M (2000) A model of competence for corpus-based machine translation. In: Proceedings of the 18th international conference on computational linguistics: COLING 2000 in Europe, Germany, pp 997–1001Google Scholar
  15. Carl M (2003) Inducing translation grammars from bracketed alignments. In: Carl and Way (2003), pp 339–361Google Scholar
  16. Carl M (2005) A system-theoretical view of EBMT. Mach Translat 19:229–249Google Scholar
  17. Carl M, Way A (eds) (2003) Recent advances in example-based machine translation. Kluwer Academic Publishers, Dordrecht, The NetherlandsGoogle Scholar
  18. Chandioux J (1976) Météo: Un système opérationnel pour la traduction automatique des bulletins météorologiques destinés au grand public [Météo: A working system for the machine translation of weather reports aimed at the general public]. META 21:127–133Google Scholar
  19. Chiang D (2005) A hierarchical phrase-based model for statistical machine translation. In: 43rd annual meeting of the Association for Computational Linguistics, Ann Arbor, MI, pp 263–270Google Scholar
  20. Cicekli I (2005) Inducing translation templates with type constraints. Mach Translat 19:281–297Google Scholar
  21. Cicekli I, Güvenir HA (1996) Learning translation rules from a bilingual corpus. In: Second international conference on new methods in language processing (NeMLaP-2), Ankara, Turkey, pp 90–97Google Scholar
  22. Cicekli I, Güvenir HA (2003) Learning translation templates from bilingual translation examples. In: Carl and Way (2003), pp 255–286Google Scholar
  23. Collins B, Somers H (2003) EBMT seen as case-based reasoning. In: Carl and Way (2003), pp 115–153Google Scholar
  24. Columbia (2005) The Columbia electronic encyclopedia. Columbia University Press, New York, NYGoogle Scholar
  25. Dummett MAE (1975) What is a theory of meaning?. In: Guttenplan S (ed) Mind and language. Oxford University Press, Oxford, England, pp 97–138Google Scholar
  26. Furuse O, Iida H (1992) Cooperation between transfer and analysis in example-based framework. In: Proceedings of the fifteenth [sic] international conference on computational linguistics, COLING-92, Nantes, France, pp 645–651Google Scholar
  27. Groves D, Hearne M, Way A (2004) Robust sub-sentential alignment of phrase-structure trees. In Coling: 20th international conference on computational linguistics, Geneva, Switzerland, pp 183–190Google Scholar
  28. Groves D, Way A (2005) Hybrid example-based SMT: The best of both worlds? In ACL-2005 Workshop on building and using parallel texts, Ann Arbor, MI, pp 183–190Google Scholar
  29. Groves D, Way A (2005) Hybrid data-driven models of machine translation. Mach Translat 19:299–321Google Scholar
  30. Hall RP (1989) Computational approaches to analogical reasoning: A comparative analysis. Artif Intell 39:39–120CrossRefGoogle Scholar
  31. Hutchins J (2005) Towards a definition of example-based machine translation. In: MT Summit X workshop: Second workshop on example-based machine translation, Phuket, Thailand, pp 63–70Google Scholar
  32. Hutchins J (2005) Example-based machine translation: A review and commentary. Mach Translat 19:197–211Google Scholar
  33. Hutchins WJ, Somers HL (1992) An introduction to machine translation. Academic Press, London, EnglandGoogle Scholar
  34. Kaji H, Kida Y, Morimoto Y (1992) Learning translation templates from bilingual text. In Proceedings of the fifteenth [sic] international conference on computational linguistics, COLING-92, Nantes, France, pp 672–678Google Scholar
  35. Kibler D, Aha DW (1997) Learning representative exemplars of concepts: An initial study. In: Fourth international workshop on machine learning, Irvine, CA, pp 24–29Google Scholar
  36. Kitano H, Higuchi T (1991) High performance memory-based translation on IXM2 massively parallel associative memory processor. In: AAAI-91: Proceedings of the ninth national conference on artificial intelligence, AAAI Press/ MIT Press, Menlo Park, CA, pp 149–154Google Scholar
  37. Koehn P, Och FJ, Marcu D (2003) Statistical phrase-based translation. In: HLT-NAACL: Human language technology conference of the North American chapter of the Association for Computational Linguistics, Edmonton, Alberta, Canada, pp 127–133Google Scholar
  38. Kolodner J (1983a) Maintaining organization in a dynamic long-term memory. Cog Sci 7:243–280CrossRefGoogle Scholar
  39. Kolodner J (1983b) Reconstructive memory, a computer model. Cog Sci 7:281–328CrossRefGoogle Scholar
  40. Langlais P, Gotti F (2006) EBMT by tree-phrasing. Mach Translat 20:1–25Google Scholar
  41. Lepage Y, Denoual E (2005) Purest ever example-based machine translation: Detailed presentation and assessment. Mach Translat 19:251–280Google Scholar
  42. Lin D, Cherry C (2003) Word alignment with cohesion constraint. In: HLT-NAACL 2003: Human language technology conference of the North American chapter of the Association for Computational Linguistics, Edmonton, Alberta, Canada, companion vol pp 49–51Google Scholar
  43. Liu Z, Wang H, Wu H (2006) Example-based machine translation based on tree-string correspondence and statistical generation. Mach Translat 20:27–44Google Scholar
  44. Locke WN, Booth AD (1955) Machine translation of languages: Fourteen essays. The Technology Press of the Massachusetts Institute of Technology, Cambridge, Mass/John Wiley, New York, NY/Chapman & Hall, London, EnglandGoogle Scholar
  45. Lu Y, Li S, Zhao T, Yang M (2002) Learning Chinese bracketing knowledge based on a bilingual language model. In: Proceedings of the 18th international conference on computational linguistics: COLING 2000 in Europe, Saarbrücken, Germany, pp 591–598Google Scholar
  46. Lu Y, Zhou M, Li S, Huang C, Zhao T (2001) Automatic translation template acquisition based on bilingual structure alignment. Comput Ling Chin Lang Proc 6:83–108Google Scholar
  47. Maas H-D (1987) The MT system susy. In King M (ed) Machine translation today: The state of the art. Edinburgh University Press, Edinburgh, Scotland, pp 209–246Google Scholar
  48. Matsumoto Y, Ishimoto H, Utsuro T (1993) Structural matching of parallel texts. In: 31st annual meeting of the Association for Computational Linguistics, Columbus, OH, pp 23–30Google Scholar
  49. McTait K, Trujillo A (1999) A language-neutral sparse-data algorithm for extracting translation patterns. In: Proceedings of the eighth international conference on theoretical and methodological issues in machine translation (TMI-99), Chester, England, pp 99–108Google Scholar
  50. Merriam-Webster (2002) Webster’s third new international dictionary. Merriam-Webster, Springfield, MAGoogle Scholar
  51. 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 (Edited review papers presented at the international NATO symposium on artificial and human intelligence), Amsterdam, The Netherlands, pp 173–180; repr. in Nirenburg et al. (2003), pp 351–354Google Scholar
  52. Nirenburg S, Somers H, Wilks Y (eds) Readings in machine translation. MIT Press, Cambridge, MAGoogle Scholar
  53. Och FJ, Ney H (2002) Discriminative training and maximum entropy models for statistical machine translation. In: 40th annual meeting of the Association for Computational Linguistics, Philadelphia, PA, pp 295–302Google Scholar
  54. Och FJ, Tillmann C, Ney H (1999) Improved alignment models for statistical machine translation. In: 1999 conference on empirical methods in natural language processing and very large corpora (EMNLPVLC-99), College Park, MD, pp 20–28Google Scholar
  55. OED (2005) Compact Oxford English dictionary of current English. Oxford University Press, Oxford, EnglandGoogle Scholar
  56. Porter BW, Bareiss ER (1986) Protos: An experiment in knowledge acquisition for heuristic classification tasks. In: First international meeting on advances in learning (IMAL), Les Arcs, France, pp 159–174Google Scholar
  57. Quirk C, Menezes A (2006) Dependency treelet translation: The convergence of statistical and example-based machine-translation? Mach Translat 20:45–66Google Scholar
  58. Russell S, Wefald E (1991) Do the right thing: Studies in limited rationality. MIT Press, Cambridge, MAGoogle Scholar
  59. Senellart J, Yang J, Rebollo A (2003) Systran intuitive coding technology. In: MT Summit IX: Proceedings of the ninth machine transaltion summit, New Orleans, USA, pp 346–353Google Scholar
  60. Simard M, Langlais P (2003) Statistical translation alignment with compositionality constraints. In: HLT/NAACL-2003 Workshop on building and using parallel texts, Edmonton, Alberta, Canada, pp 19–22Google Scholar
  61. Somers H (1999) Review article: Example-based machine translation. Mach Translat 14:113–157CrossRefGoogle Scholar
  62. Somers H (2003) An overview of EBMT. In: Carl and Way (2003), pp 3–57Google Scholar
  63. Stanfill C, Waltz D (1988) The memory based reasoning paradigm. In: Case-based reasoning: Proceedings from a workshop, Morgan Kaufmann, San Mateo, CA, pp 414–424Google Scholar
  64. Sumita E (2003) An example-based machine translation system using DP-matching between word sequences. In: Carl and Way (2003) pp 189–209Google Scholar
  65. Sumita E, Iida H (1991) Experiments and prospects of example-based machine translation. In: 29th annual meeting of the Association for Computational Linguistics, Berkeley, CA, pp 185–192Google Scholar
  66. Toma P (1976) An operational machine translation system. In: Brislin R (ed) Translation: Applications and research, Gardner Press, New York, NY, pp 247–259Google Scholar
  67. Toma P (1977) Systran as a multilingual machine translation system. In: Overcoming the language barrier: Third European congress on information systems and networks, Luxembourg, May 1977, Verlag Dokumentation, München, pp 569–581Google Scholar
  68. Turcato D, Popowich F (2003) What is example-based machine translation? In Carl and Way (2003), pp 59–81Google Scholar
  69. Vauquois B (1975) La traduction automatique à Grenoble [Machine translation in Grenoble]. Dunod, Paris, FranceGoogle Scholar
  70. Vauquois B, Boitet C (1985) Automated translation at Grenoble University. Comput Ling 11, 28–36Google Scholar
  71. Veale T, Way A (1997) Gaijin: A bootstrapping, template-driven approach to example-based machine translation. In: International conference, recent advances in natural language processing, Tzigov Chark, Bulgaria, pp 239–244Google Scholar
  72. Veloso MM, Carbonell JG (1993) Derivational analogy in Prodigy. Mach Learn 10:249–278CrossRefGoogle Scholar
  73. Vilar JM, Vidal E (2005) A recursive statistical translation model. In ACL-2005 Workshop on building and using parallel texts, Ann Arbor, MI, pp 199–207Google Scholar
  74. Way A, Gough N (2005) Comparing example-based and statistical machine translation. Nat Lang Eng 11:295–309CrossRefGoogle Scholar
  75. Weaver W (1949) Translation. In: Locke and Booth (1955) pp 15–23; repr. in Nirenburg (2003), pp 13–17Google Scholar
  76. WordNet (2003) WordNet 2.0. Cognitive Science Laboratory, Princeton University, Princeton, NJGoogle Scholar
  77. Wu D (1995a) An algorithm for simultaneously bracketing parallel texts by aligning words. In: 33rd annual meeting of the Association for Computational Linguistics, Cambridge, MA, pp 244–251Google Scholar
  78. Wu D (1995b) Trainable coarse bilingual grammars for parallel text bracketing. In: 3rd annual workshop on very large corpora (WVLC-3), Cambridge, MA, pp 69–81Google Scholar
  79. Wu D (1996) A polynomial-time algorithm for statistical machine translation. In: 34th annual meeting of the Association for Computational Linguistics, Santa Cruz, CA, pp 152–158Google Scholar
  80. Wu D (1997) Stochastic inversion transduction grammars and bilingual parsing of parallel corpora. Comput Ling 23:377–404Google Scholar
  81. Wu D (2000) Alignment. In: Dale R, Moisl H, Somers H (eds) Handbook of natural language processing. Marcel Dekker, New York, NY, pp 415–458Google Scholar
  82. Wu D (2005) Recognizing paraphrases and textual entailment using inversion transduction grammars. In: ACL-2005 workshop on empirical modeling of semantic equivalence and entailment, Ann Arbor, MI, pp 25–30Google Scholar
  83. Wu D, Fung P (2005) Inversion transduction grammar constraints for mining parallel sentences from quasi-comparable corpora. In: Second international joint conference on natural language processing (IJCNLP-2005), Jeju, Korea, pp 257–268Google Scholar
  84. Wu D, Wong H (1998) Machine translation with a stochastic grammatical channel. In: COLING-ACL ’98: 36th annual meeting of the Association for Computational Linguistics and 17th international conference on computational linguistics, Montreal, Quebec, Canada, pp 1408–1415Google Scholar
  85. Yamada K, Knight K (2001) A syntax-based statistical translation model. In: Association for Computational Linguistics 39th annual meeting and 10th conference of the European chapter, Toulouse, France, pp 523–529Google Scholar
  86. Yamamoto K, Matsumoto Y (2003) Extracting translation patterns from parallel corpora. In: Carl and Way (2003), pp 365–395Google Scholar
  87. Zens R, Ney H (2003) A comparative study on reordering constraints in statistical machine translation. In: 41st annual meeting of the Association for Computational Linguistics, Sapporo, Japan, 192–202Google Scholar
  88. Zens R, Ney H, Watanabe T, Sumita E (2004) Reordering constraints for phrase-based statistical machine translation. In: Coling: 20th international conference on computational linguistics, Geneva, Switzerland, pp 205–211Google Scholar
  89. Zhang H, Gildea D (2005) Stochastic lexicalized inversion transduction grammar for alignment. In: 43rd annual meeting of the Association for Computational Linguistics, Ann Arbor, MI, pp 475–482Google Scholar
  90. Zhang Y, Vogel S (2005) An efficient phrase-to-phrase alignment model for arbitrarily long phrase and large corpora. In: Proceedings of the 10th annual conference of the European Association for Machine Translation, Budapest, Hungary, pp 294–301Google Scholar
  91. Zhao B, Vogel S (2003) Word alignment based on bilingual bracketing. In HLT/NAACL-2003 workshop on building and using parallel texts, Edmonton, Alberta, Canada, pp 15–18Google Scholar

Copyright information

© Springer Science+Business Media 2007

Authors and Affiliations

  1. 1.Department of Computer Science, HKUST Human Language Technology CenterHong Kong University of Science and TechnologyKowloonHong Kong

Personalised recommendations