Er maskinoversetting fra nordsamisk nyttig for sørsamisk?
DOI:
https://doi.org/10.7557/12.6342Keywords:
machine translation, rule-based, South SaamiAbstract
The article assesses the strengths and weaknesses of a rule-based translation program from North Saami to South Saami. As a tool for translators, the system can contribute to more text being produced in South Saami, both by using North Saami as an intermediary in the translation of texts from Norwegian and Swedish, and by translating texts that are originally written in North Saami. The system may also help teachers in academia to understand texts written by South Saami students. The system is still not good enough, in particular the number of word pairs in the lexicon must be increased considerably to get a better result. The translation is also not robust with respect to linguistic errors in the North Saami text. The linguistic difference between North Saami and South Saami syntax is big, and one could consider whether it would be appropriate to use a rule-based approach, which allows using information about the sentences' dependency trees, in order to more easily transform the sentences from North Saami syntax to acceptable South Saami.
References
Antonsen, Lene, Trond Trosterud og Francis M. Tyers. 2016. A North Saami to South Saami Machine Translation Prototype. NEJLT vol. 4. Tilgjengelig på https://doi.org/10.3384/nejlt.2000-1533.1642 https://doi.org/10.3384/nejlt.2000-1533.1642
Antonsen, Lene og Trond Trosterud. 2017. Ord sett innafra og utafra – en datalingvistisk analyse av nordsamisk. Norsk lingvistisk tidsskrift. Volum 35:2, s. 153–185. Tilgjengelig på https://hdl.handle.net/10037/13250
Antonsen, Lene og Trond Trosterud. 2020. Med et tastetrykk. Bruk av digitale ressurser for samiske språk. / Boallobeavddi bokte. Sámegielaid digitála resurssaid geavaheapmi. I Sámi logut muitalit 13. Čielggaduvvon sámi statistihkka 2020 / Samiske tall forteller 13. Kommentert samisk statistikk 2020. Guovdageaidnu: Sámi allaskuvla. Tilgjengelig på https://samilogutmuitalit.no/se/node/4105
Antonsen, Lene, Ciprian Gerstenberger, Maja Kappfjell, Sandra Nystø Rahka, Marja-Liisa Olthuis, Trond Trosterud og Francis M. Tyers. 2017. Machine translation with North Saami as a pivot language. Proceedings of the 21st Nordic Conference on Computational Linguistics, NoDaLiDa, 22–24 May 2017, Gothenburg, Sweden. Number 131 in Linköping Electronic Conference Proceedings. Linköping University Electronic Press, Linköpings universitet. s. 123–131. Tilgjengelig på https://ep.liu.se/ecp/131/015/ecp17131015.pdf
Bick, Eckhard. 2007. Dan2eng: Wide-Coverage Danish-English Machine Translation. Proceedings of Machine Translation Summit XI. s. 37–43. Tilgjengelig på https://aclanthology.org/2007.mtsummit-papers.6.pdf
Bick, Eckhard. 2011. WikiTrans: the English Wikipedia in Esperanto. In Constraint Grammar Applications, Workshop Proceedings at Nodalida. Vol. 14, s. 8–16. Tilgjengelig på http://hdl.handle.net/10062/19297
Forcada M.L., M. Ginestí-Rosell, J. Nordfalk, J. O’Regan, S. Ortiz-Rojas, J.A. Pérez-Ortiz, F. Sánchez-Martínez, G. Ramírez-Sánchez og F.M. Tyers. 2011. Apertium: a free/open-source platform for rule-based machine translation. Machine Translation 25(2):127–144. Tilgjengelig på https://link.springer.com/article/10.1007/s10590-011-9090-0, https://doi.org/10.1007/s10590-011-9090-0 https://doi.org/10.1007/s10590-011-9090-0
Khanna, T., J.N. Washington, F.M. Tyers, S. Bayatl, D. Swanson, T.A. Pirinen, I. Tang og H. Alòs. 2021. Recent advances in Apertium, a free/open-source rule-based machine translation platform for low-resource languages. Machine Translation. Tilgjengelig på https://doi.org/10.1007/s10590-021-09260-6 https://doi.org/10.1007/s10590-021-09260-6
Magga, Ole Henrik og Lajla Mattsson Magga. 2012. Sørsamisk grammatikk. Davvi Girji.
Nickel, Klaus Peter og Pekka Sammallahti. 2011. Nordsamisk grammatikk. Davvi Girji.
Trosterud, Trond og Lene Antonsen. 2020. Hva er viktig for forståelse? Om maskinoversetting fra nordsamisk. – K. Hagen, A. Hjelde, K. Stjernholm og Ø. A. Vangsnes (red.): Bauta: Janne Bondi Johannessen in memoriam. Oslo Studies in Language, 11(2): 489–502. Oslo: University of Oslo. Tilgjengelig på https://doi.org/10.5617/osla.8514 https://doi.org/10.5617/osla.8514
Downloads
Published
Issue
Section
License
Copyright (c) 2023 Lene Antonsen
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.