Opentrad Apertium Open-Source Machine Translation System: an Opportunity for Business and Research

What it is about

A position paper from the Opentrad project that argues for open-source machine translation in both research and business. It separates open-source MT from closed MT, and splits each system into an engine and its data. It surveys the licences in use (GPL, LGPL, BSD-style, MPL, and Creative Commons for documentation and data) and the hosting sites for projects. It then presents Apertium as a shallow-transfer engine, with its eight modules and XML data formats, and reports the state of the pilot pairs: about 10,000 lemmas and under 80 transfer rules per pair, with an error rate of roughly 5 to 10 percent on general texts between related languages. The paper's point is that small open lexicons, improved by many contributors, can already be useful.

Ideas

• I1. Plot quality against data size for the translator's concept lexicon. Apertium's pilot pairs suggest that a small curated table already gives usable output on close pairs. In tools/translate, record the exact-match rate per author as merges are added, and find where the next merge stops paying.
• I2. Put the licence of every data source into the build. A concept table or author delta built from an NC or research-only source must be flagged, and a release build should refuse it. This follows licence/DATA.md and the rule that NC data is used only for tests.
• I3. Allow contributors to add author deltas as small data files, each with its own held-out check. The open-source argument is that the community improves data, not the engine, so the delta format should be readable and checkable by a non-programmer.

For Mova

The code is tools/translate (meta.rs for the concept lexicon, and the author-delta loader) and the build script that assembles the release. The quality-versus-size curve belongs in measure.rs. The paper is mainly about licences and business, so its ideas for Mova are about data handling, not the translator's algorithm.

Topics: Machine translation

Cite

The paper itself, not this card. BibTeX from the library's record of the work.

@inproceedings{ramirezsanchez2006opentrad,
  title = {{Opentrad Apertium Open-Source Machine Translation System: an Opportunity for Business and Research}},
  author = {Ramirez-Sánchez, Gema},
  booktitle = {Proceedings of Translating and the Computer 28},
  year = {2006},
  url = {https://aclanthology.org/2006.tc-1.12/}
}

References

10 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Armentano-Oller, C., Carrasco, R. C., Corbı́-Bellot, A. M., Forcada, M. L., Ginestı́-Rosell, M., Ortiz-Rojas, S., Pérez-Ortiz, J. A., Ramı́rez-Sánchez, G., Sánchez-Martı́nez, F., and 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, volume 3960 of Lecture Notes in Computer Science, pages 50–59. Springer-Verlag. find
2. Behlendorf, B. (1999). Open Sources: Voices from the Open Source Revolution, chapter Open Source as a Business Strategy. O’reilly. Edited by Chris DiBona, Sam Ockman, Mark Stone. find
3. Canals-Marote, R., Esteve-Guillen, A., Garrido-Alenda, A., Guardiola-Savall, M., Iturraspe-Bellver, A., Montserrat-Buendia, S., Ortiz-Rojas, S., Pastor-Pina, H., Perez-Antón, P. M., and Forcada, M. L. (2001). The Spanish-Catalan machine translation system interNOSTRUM. In Proceedings of MT Summit VIII: Machine Translation in the Information Age, pages 73–76. Santiago de Compostela, Spain, July. find
4. Corbı́-Bellot, A. M., Forcada, M. L., Ortiz-Rojas, S., Pérez-Ortiz, J. A., Ramı́rez-Sánchez, G., Sánchez-Martı́nez, F., Alegria, I., Mayor, A., and Sarasola, K. (2005). An open-source shallow-transfer machine translation engine for the Romance languages of Spain. In Proceedings of the 10th European Associtation for Machine Translation Conference, pages 79–86, Budapest, Hungary. find
5. Cutting, D., Kupiec, J., Pedersen, J., and Sibun, P. (1992). A practical part-of-speech tagger. In Third Conference on Applied Natural Language Processing. Association for Computational Linguistics. Proceedings of the Conference., pages 133–140, Trento, Italy. find
6. de Medeiros Caseli, H. and Nunes, M. G. V. (2006). Automatic transfer rule induction from parallel corpora. In Proceedings of III Workshop on MSc dissertation and PhD thesis in Artificial Inteligence (WTDIA’2006), SBIA’2006. (to be published). find
7. Forcada, M. L. (2006). Open-source machine translation: an opportunity for minor languages. In Proceedings of Strategies for developing machine translation for minority languages (5th SALTMIL workshop on Minority Languages). find
8. Garrido-Alenda, A., Forcada, M. L., and Carrasco, R. C. (2002). Incremental construction and maintenance of morphological analysers based on augmented letter transducers. In Proceedings of TMI 2002 (Theoretical and Methodological Issues in Machine Translation), pages 53–62. find
9. Garrido-Alenda, A., Gilabert Zarco, P., Pérez-Ortiz, J. A., Pertusa-Ibáñez, A., Ramı́rez-Sánchez, G., Sánchez-Martı́nez, F., Scalco, M. A., and Forcada, M. L. (2004). Shallow parsing for Portuguese-Spanish machine translation. In Branco, A., Mendes, A., and Ribeiro, R., editors, Language technology for Portuguese: shallow processing tools and resources, pages 135–144. Lisboa. find
10. Sánchez-Martı́nez, F., Pérez-Ortiz, J. A., and Forcada, M. L. (2006). Speeding up target-language driven part-of-speech tagger training for machine translation. In Advances in Artificial Intelligence, Proceedings of the 5th MICAI, volume 4293 of Lecture Notes in Computer Science, pages 844–854. Springer-Verlag. Accepted. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/sanchez-2006-opentrad-apertium-open-source-machine/