Development of a short bilingual translation service based on a distributed annotated information processing system
K.F. Krai, A.Z. Enes
Upload the full text
Abstract.The development of a service for short bilingual translations is an urgent task of the creation of automatic text translation systems for medium and small languages, for which there are no annotated databases necessary for training. As part of this work, a system is being implemented for automatically translating short texts from one language to another, the feature of which is the use of a distributed architecture for collecting, processing, storing and using information provided by system users based on the original motivation model, which allows you to significantly increase the speed of creating a training sample and the quality of translation processing.
Keywords: machine learning, distributed system, natural language processing, data collection, web service, crowdsourcing, machine translation, artificial intelligence, information annotation, text analysis, translation, text, information processing
For citation. Krai K.F., Enes A.Z. Development of a short bilingual translation service based on a distributed annotated information processing system. News of the Kabardino-Balkarian Scientific Center of RAS. 2024. Vol. 26. No. 3. Pp. 21–31. DOI: 10.35330/1991-6639-2024-26-3-21-31
References
- Schultz T., Kirchhoff K. Multilingual speech processing. 2006. ISBN: 9780080457628
- Bisani M., Ney H. Joint-sequence models for grapheme-to-phoneme conversion. Speech Communication. 2008. Vol. 50. No. 5. Pp. 434–451. DOI: 10.1016/j.specom.2008.01.002.hal-00499203
- Kartseva E.Yu., Margaryan T.D., Gurova G.G. Razvitie mashinnogo perevoda i ego mesto v professional’noy mezhkul’turnoy kommunikacii [Development of machine translation and its place in professional intercultural communication]. RUDN journal of language studies, semiotics and semantics. 2016. No. 3. Pp. 155–164. EDN: WHBQCV. (In Russian)
- Corney J., Lynn A., Torres-Sanchez C. et al. Towards crowdsourcing translation tasks in library cataloguing, a pilot study. 4th IEEE International conference on digital ecosystems and technologies. Dubai. United Arab Emirates. 2010. Pp. 572–577. DOI: 10.1109/DEST. 2010.5610593
- Jiménez-Crespo M.A. Crowdsourcing and online collaborative translations. 2017. Amsterdam/Philadelphia: John Benjamins Publishing Company. 320 p. ISBN: 1932–8036/2017BKR0009
- Certificate of state registration of a computer program No. 2024610266 Russian Federation. Programma dlya sozdanija i podderzhki infrastruktury mashinnogo obucheniya mul’tiagentnoy nejrokognitivnoy sistemy prinjatiya resheniy ponimaniyu vyskazyvaniy [Program for creating and supporting machine learning infrastructure for a multi-agent neurocognitive decision-making system for understanding statements]. No. 2023688479: application. 12/19/2023: publ. 01/09/2024 /A.Z. Enes, Z.V. Nagoev, K.F. Krai. Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences. EDN: IRFXLN. (In Russian)
- Certificate of state registration of a computer program No. 2024610267 Russian Federation. Programma dlya raspredelennoy platformy audio perevodov [Program for a distributed audio translation platform]: No. 2023688483: application. 12/19/2023: publ. 01/09/2024 / A.Z. Enes, Z.V. Nagoev, K.F. Krai. Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences. EDN: GGOBJH. (In Russian)
- McDonough D.J. Analyzing the сrowdsourcing model and its impact on public perceptions of translation. The Translator. 2012. No. 18(2). Pp. 167–191. DOI: 10.1080/13556509.2012.10799507
- Yasir M., Akbar Kh., Bashir M. The Impact of artificial intelligence on language translation: A Review. IEEE Access. 2024. No. 12. Pp. 25553–25579. DOI: 10.1109/ACCESS.2024.3366802
Information about the authors
Karina F. Krai, Junior Researcher of the Laboratory of Computational Linguistics, Institute of Computer Science and Problems of Regional Management – branch of Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences;
360000, Russia, Nalchik, 37-a I. Armand street;
kraykarina@mail.ru, ORCID: https://orcid.org/0000-0002-6927-7361, SPIN-code: 5967-0267
Akhmed Z. Enes, Junior Researcher of the Laboratory of Computational Linguistics, Institute of Computer Science and Problems of Regional Management – branch of Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences;
360000, Russia, Nalchik, 37-a I. Armand street;
ahmedenes@mail.ru, ORCID: https://orcid.org/0000-0003-3633-4910, SPIN-code: 3643-1808