Abstract
A mechanism for learning lexical correspondences between two languages from sets of translated sentence pairs is presented. These lexical level correspondences are learned using analogical reasoning between two translation examples. Given two translation examples, the similar parts of the sentences in the source language must correspond to the similar parts of the sentences in the target language. Similarly, the different parts must correspond to the respective parts in the translated sentences. The correspondences between similarities and between differences are learned in the form of translation templates. A translation template is a generalized translation exemplar pair where some components are generalized by replacing them with variables in both sentences and establishing bindings between these variables. The learned translation templates are obtained by replacing differences or similarities by variables. This approach has been implemented and tested on a set of sample training datasets and produced promising results for further investigation.
Similar content being viewed by others
References
K. Goodman and S. Nirenburg, KBMT-89: A Case Study in Knowledge Based Machine Translation, Morgan Kaufmann: San Mateo, CA, 1992.
T. Mitumura and E. Nyberg, “The KANT system: Fast, accurate, high-quality translation in practical domains, in Proceedings of COLING-92, Nantes, France, 1992, pp. 1069-1073.
D. Lonsdale, T. Mitamura, and E. Nyberg, Acquisition of Large Lexicons for Practical Knowledge-Based MT, Machine Translation, vol 9, no. 3, Kluwer Academic Publishers, Dordrecht, 1994, pp. 251-283.
M.A. Nagao, “Framework of a mechanical translation between Japanese and English by analogy principle,” in Artificial and Human Intelligence, edited by A. Elithorn and R Banerji, NATO Publications: North-Holland, Edinburg, 1984, pp. 173-180.
O. Furuse and H. Iida, “Cooperation between transfer and analysis in example-based framework,” in Proceedings of COLING-92, Nantes, France, 1992, pp. 645-651.
H. Kitano, “A comprehensive and practical model of memory-based machine translation,” in Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence, Morgan Kaufmann, 1993, pp. 1276-1282.
S. Sato and M. Nagao, “The memory-based translation,” in Proceedings of COLING-90, 1990.
S. Sato, “MBT2: A method for combining fragments of examples in example-based translation,” Artificial Intelligence, vol. 75, Elsevier Science, MA, 1995, pp. 31-50.
F. Smadja, K.R. McKeown, and V. Hatzivassiloglou, Translating Collocation for Bilingual Lexicons: A Statistical Approach, Computational Linguistics, vol. 22, no. 1, The MIT Press: Cambridge, MA, 1996, pp. 1-38.
E. Sumita and H. Iida, “Experiments and prospects of example-based machine translation,” in Proceedings of the 29th Annual Meeting of the Association for Computational Linguistics, 1991.
R.D. Brown, “Automated dictionary extraction for “knowledge-free” example-based translation,” in Proceedings of TMI'97, 1997.
D. Wu and X. Xia, Large-Scale Automatic Extraction of an English-Chinese Translation Lexicon, Machine Translation, vol. 9, Kluwer Academic Publishers, Dordrecht, 1995, pp. 285-313.
C. Brona and C. Padraig, “Translating software documentation by example: An EBMT approach to machine translation,” in Proceedings of Int. ECAI Workshop: Multilinguality in the Software Industry, 1996.
R.D. Brown, “Example-based machine translation in the Pangloss system,” in Proceedings of COLING-96, 1996.
S. Nirenburg, S. Beale, and C. Domashnev, “A full-text experiment in example-based machine translation,” in Proceedings of the International Conference on New Methods in Language Processing, NeMLap, Manchester, UK, 1994, pp. 78-87.
H. Kaji, Y. Kida, and Y. Morimoto, “Learning translation templates from bilingual text,” in Proceedings of COLING-92, 1992, pp. 672-678.
H.A. Güvenir and A. Tunç, “Corpus-based learning of generalized parse tree rules for translation,” in New Directions in Artificial Intelligence: Proceedings of the 11th Biennial Conference of the Canadian Society for Computational Studies of Intelligence, edited by G. McCalla LNCS 1081, Toronto, Ontario, Canada, May 1996, Springer Verlag, pp. 121-131.
D.L. Medin and M.M. Schaffer, “Context theory of classification learning,” Psychological Review, vol. 85, pp. 207-238, 1978.
K.J. Hammond, (Ed.), Proceedings: Second Case-Based Reasoning Workshop, Pensacola Beach, FL, Morgan Kaufmann, MA 1989.
J.L. Kolodner, (Ed.), in Proceedings of a Workshop on Case-Based Reasoning, Clearwater Beach, FL, Morgan Kaufmann, 1988.
A. Ram, “Indexing, elaboration and refinement: Incremental learning of explanatory cases, in Case-Based Learning, edited by Janet L. Kolodner, Kluwer Academic Publishers: Dordrecht, 1993.
I. Cicekli and H.A. Güvenir, “Learning translation rules from a bilingual corpus,” in Proceedings of the 2nd International Conference on New Methods in Language Processing (NeMLaP-2), Ankara, Turkey, September 1996, pp. 90-97.
H.A. Güvenir and I. Cicekli, “Learning translation templates from examples,” Information Systems, vol. 23, no. 6, pp. 353-363, 1998.
G. Gazdar, E. Klein, G.K. Pullum, and I.A. Sag, Generalized Phrase Structure Grammar, Blackwell: Cambridge, Mass., 1985.
I.A. Sag and C. Pollard, “Head-driven phrase structure grammar: An informal synopsis,” CSLI Technical Report CSLI-87-79, Stanford, 1987.
Z. Öz and I. Cicekli, Ordering Translation Templates by Assigning ConfidenceFactors, in Proceedings ofAMTA'98, Langhorne, PA, Lecture Notes in Computer Science 1529, Springer Verlag, 1998, pp. 51-61.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Cicekli, I., Güvenir, H.A. Learning Translation Templates from Bilingual Translation Examples. Applied Intelligence 15, 57–76 (2001). https://doi.org/10.1023/A:1011270708487
Issue Date:
DOI: https://doi.org/10.1023/A:1011270708487