Inferring Shallow-Transfer Machine Translation Rules from Small Parallel Corpora

What it is about

A longer and fuller version of the 2007 method. Shallow-transfer rules are inferred from sentence-aligned corpora that are small compared with those used for statistical MT. The method is unsupervised. It uses alignment templates, extended with restrictions taken from the dictionary of the MT system so that each learned rule reproduces only what the dictionary can produce. Word alignments come from GIZA++ with IBM models 1, HMM, 3 and 4, and the paper explains how the parallel corpora were prepared. The method is tested on three language pairs in Apertium with corpora of different sizes. Quality rises over word-for-word translation and approaches that of hand-coded rules. The paper reports confidence intervals with each score, so that small differences can be read against their noise, and it analyses the inferred rules one by one. The rules are human-readable and can be edited.

Ideas

• I1. Attach a bootstrap confidence interval to every translator number, and use a paired bootstrap for each delta. The current gate (a delta must fix at least three more tokens and hold in at least half of its contexts) is a count rule; a paired test on the token-level differences would show when a delta's gain is noise.
• I2. Plot quality against training size, from a small sample up to the whole set, for each author. This shows where a new author's data is enough and where more verses stop helping.
• I3. Export every learned delta as one readable line with its evidence (the tokens it fixes, and the contexts where it holds), so that a linguist can edit or reject it, as the paper's rules can be edited. This is also the form in which a reviewer checks a delta.
• I4. Analyse the inferred rules one by one. For each delta, list what it changes in the held-out text and what it breaks; a delta that fixes three tokens and breaks two is visible in this table.

For Mova

The code is tools/translate, the delta learner and measure.rs. The confidence intervals belong in measure.rs, and the readable export in the delta writer. The paper's dictionary restrictions match the guards already discussed for martinez-2007. Its results are for shallow rules, so the numbers are only a comparison point; the habits of reporting and of per-rule analysis are what carry over.

Topics: Machine translation

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.1613/jair.2735 · arXiv 1401.5700

@misc{sanchezmartinez2014inferring,
  title = {{Inferring Shallow-Transfer Machine Translation Rules from Small Parallel Corpora}},
  author = {Sanchez-Martinez, Felipe and Forcada, Mikel L.},
  year = {2014},
  doi = {10.1613/jair.2735},
  eprint = {1401.5700},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.1613/jair.2735}
}

References

43 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Alcázar, A. (2005). Towards linguistically searchable text. In Proceedings of BIDE (Bilbao-Deusto) Summer School of Linguistics 2005, Bilbao. Universidad de Deusto. find
2. Armentano-Oller, C., Carrasco, R. C., CorbÃ-Bellot, A. M., Forcada, M. L., Ginestı́-Rosell, M., Ortiz-Rojas, S., Pérez-Ortiz, J. A., Ramı́rez-Sánchez, G., Sánchez-Martı́nez, F., & Scalco, M. A. (2006). Open-source Portuguese-Spanish machine translation. In Computational Processing of the Portuguese Language, Proceedings of the 7th International Workshop on Computational Processing of Written and Spoken Portuguese, PROPOR 2006, Vol. 3960 of Lecture Notes in Computer Science, pp. 50–59. Springer-Verlag. find
3. Arnold, D. (2003). Why translation is difficult for computers. In Computers and Translation: A translator’s guide. Benjamins Translation Library. find
4. Baum, L. E., & Petrie, T. (1966). Statistical inference for probabilistic functions of finite state Markov chains. The Annals of Mathematical Statistics, 37 (6), 1554–1563. find
5. Brown, P. F., Pietra, S. A. D., Pietra, V. J. D., & Mercer, R. L. (1993). The mathematics of statistical machine translation: Parameter estimation. Computational Linguistics, 19 (2), 263–311. find
6. Brown, R. D. (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), pp. 22–32. find
7. Carl, M., & Way, A. (Eds.). (2003). Recent Advances in Example-Based Machine Translation, Vol. 21. Springer. find
8. Caseli, H. M., Nunes, M. G. V., & Forcada, M. L. (2005). LIHLA: A lexical aligner based on language-independent heuristics. In Anais do V Encontro Nacional de Inteligà a ncia Artificial (ENIA 2005), pp. 641–650. 24. The XML formats (http://www.w3.org/XML/) for each type of linguistic data are defined through conveniently-designed XML document-type definitions (DTDs) which may be found inside the Apertium package. ↗
9. Caseli, H. M., Nunes, M. G. V., & Forcada, M. L. (2006). Automatic induction of bilingual resources from aligned parallel corpora: application to shallow-transfer machine translation. Machine Translation, 20 (4), 227–245. Published in 2008. find
10. Cicekli, I., & Güvenir, H. A. (2001). Learning translation templates from bilingual translation examples. Applied Intelligence, 15 (1), 57–76. find
11. Cutting, D., Kupiec, J., Pedersen, J., & Sibun, P. (1992). A practical part-of-speech tagger. In Proceedings of the Third Conference on Applied Natural Language Processing. Association for Computational Linguistics, pp. 133–140. find
12. Efron, B., & Tibshirani, R. J. (1994). An introduction to the Bootstrap. CRC Press. find
13. Gough, N., & Way, A. (2004). Robust large-scale EBMT with marker-based segmentation. In Proceedings of the 10th International Conference on Theoretical and Methodological Issues in Machine Translation, pp. 95–104, Baltimore, MD. find
14. Green, T. (1979). The necessity of syntax markers. Two experiments with artificial languages. Journal of Verbal Learning and Behavior, 18, 481–496. find
15. Hutchins, W. J., & Somers, H. L. (1992). An Introduction to Machine Translation. Academic Press. find
16. Kaji, H., Kida, Y., & Morimoto, Y. (1992). Learning translation templates from bilingual text. In Proceedings of the 14th Conference on Computational Linguistics, pp. 672– 678. Association for Computational Linguistics. find
17. Knight, K. (1999). A statistical machine translation tutorial workbook. 35 pages. (http://www.isi.edu/natural-language/mt/wkbk.rtf). find
18. Koehn, P. (2004). Statistical significance tests for machine translation evaluation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 388–395. find
19. 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 Annual Meeting of the Association for Computational Linguistics (ACL), demonstration session. find
20. Lavie, A., Probst, K., Peterson, E., Vogel, S., Levin, L., Font-Llitjós, A., & Carbonell, J. (2004). A trainable transfer-based machine translation approach for languages with limited resources. In Proceedings of Workshop of the European Association for Machine Translation (EAMT-2004). find
21. Liu, Y., & Zong, C. (2004). The technical analysis on translation templates. In Proceedings of the IEEE International Conference on Systems, Man & Cybernetics (SMC), pp. 4799–4803. IEEE. find
22. Menezes, A., & Richardson, S. D. (2001). A best-first alignment algorithm for automatic extraction of transfer mappings from bilingual corpora. In Proceedings of the ACL Workshop on data-driven machine translation, pp. 39–46. find
23. Mikheev, A. (1996). Unsupervised learning of word-category guessing rules. In Proceedings of the Thirty-Fourth Annual Meeting of the Association for Computational Linguistics, pp. 327–333. find
24. Nagao, M. (1984). A framework of a mechanical translation between English and Japanese by analogy principle. In Elithorn, A., & Banerji, R. (Eds.), Artifical and Human Intelligence, pp. 173–180. North-Holland. find
25. Och, F. J. (1999). An efficient method for determining bilingual word classes. In EACL’99: Ninth Conference of the European Chapter of the Association for Computational Lingustics, pp. 71–76. find
26. Och, F. J. (2002). Statistical machine translation: From single-word models to alignment templates. Ph.D. thesis, RWTH Aachen University. (http://www-i6.informatik.rwth-aachen.de/publications/download/520/Och--2002.pdf). ↗
27. Och, F. J. (2003). Minimum error rate training in statistical machine translation. In 41st Annual Meeting of the Association for Computational Linguistics, pp. 160–167, Sapporo, Japan. find
28. Och, F. J. (2005). Statistical machine translation: Foundations and recent advances. Tutorial at MT Summit X. (http://www.mt-archive.info/MTS-2005-Och.pdf). ↗
29. Och, F. J., & Ney, H. (2002). Discriminative training and maximum entropy models for statistical machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Lingustics (ACL), pp. 295–302. find
30. Och, F. J., & Ney, H. (2003). A systematic comparison of various statistical alignment models. Computational Linguistics, 29 (1), 19–51. find
31. Och, F. J., & Ney, H. (2004). The alignment template approach to statistical machine translation. Computational Linguistics, 30 (4), 417–449. find
32. Papineni, K., Roukos, S., Ward, T., & Zhu, W. J. (2002). BLEU: a method for automatic evaluation of machine translation. In Proceeding of 40th Annual meeting of the Association for Computational Linguistics, pp. 311–318. find our card
33. Probst, K., Levin, L., Peterson, E., Lavie, A., & Carbonell, J. (2002). MT for minority languages using elicitation-based learning of syntactic transfer rules. Machine Translation, 17 (4), 245–270. find
34. Sánchez-Martı́nez, F., & Forcada, M. L. (2007). Automatic induction of shallow-transfer rules for open-source machine translation. In Proceedings of the 11th Conference on Theoretical and Methodological Issues in Machine Translation (TMI 2007), pp. 181– 190. find our card
35. Sánchez-Martı́nez, F., & Ney, H. (2006). Using alignment templates to infer shallow-transfer machine translation rules. In Lecture Notes in Computer Science 4139, Proceedings of FinTAL, 5th International Conference on Natural Language Processing, pp. 756–767. find
36. Sánchez-Martı́nez, F., Pérez-Ortiz, J. A., & Forcada, M. L. (2008). Using target-language information to train part-of-speech taggers for machine translation. Machine Translation, 22 (1-2), 29–66. find
37. Simões, A., & Almeida, J. (2003). NATools - a statistical word aligner workbench. Procesamiento del Lenguaje Natural, 31, 217–224. find
38. Snover, M., Dorr, B., Schwartz, R., Micciulla, L., & Makhoul, J. (2006). A study of translation edit rate with targeted human annotation. In Proceedings of the 7th Conference of the Association for Machine Translation in the Americas, “Visions for the Future of Machine Translation”, pp. 223–231, Cambridge, MA, USA. find our card
39. Steinberger, R., Pouliquen, B., Widiger, A., Ignat, C., Erjavec, T., Tufis, D., & Varga, D. (2006). The JRC-Acquis: A multilingual aligned parallel corpus with 20+ languages. In Proceedings of the 5th International Conference on Language Resources and Evaluation (LREC). find
40. Stolcke, A. (2002). SRILM – an extensible language modeling toolkit. In Proceedings of the International Conference on Spoken Language Processing, pp. 901–904, Denver, CO. find
41. Tyers, F. M., Dugast, L., & Park, J. (2009). Rule-based augmentation of training data in Breton–French statistical machine translation. In Proceedings of the 13th Annual Conference of the European Associtation for Machine Translation, Barcelona, Spain. In press. find
42. Vogel, S., Ney, H., & Tillmann, C. (1996). HMM-based word alignment in statistical translation. In COLING ’96: The 16th International Conference on Computational Linguistics, pp. 836–841. find
43. Zens, R., Och, F. J., & Ney, H. (2002). Phrase-based statistical machine translation. In KI 2002: Advances in Artificial Intelligence: Proceedings 25th Annual German Conference on AI, Vol. 2479 of Lecture Notes in Computer Science, pp. 18–32. Springer-Verlag. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/sanchez-2014-martinez-inferring-shallow-transfer-machine-translation/