Elamur Research⌕
☰
home / papers / 2026 / SemiAdapt: Semi-Supervised and Efficient LoRA-Based Domain Adaptation for Low-Resource Irish Machine Translation with Transformers

SemiAdapt: Semi-Supervised and Efficient LoRA-Based Domain Adaptation for Low-Resource Irish Machine Translation with Transformers

Summary

The paper addresses English-to-Irish machine translation, a direction that large multilingual models such as NLLB-200 handle poorly. Irish is rarely a target language in their training, it has rich morphology, and parallel data is scarce. Full fine-tuning of billion-parameter models is also too costly for many low-resource researchers. The authors propose two semi-supervised methods. SemiAdapt-Full and SemiAdapt-LoRA first assign domain labels to individual training sentences in a zero-shot way. They then either fine-tune the whole model or train a separate LoRA adapter for each domain. At inference, domain embedding centroids decide which domain a sentence belongs to. In the LoRA variant, a single shared base model then switches to the matching lightweight adapter. SemiAdapt-Full can beat ordinary full fine-tuning. SemiAdapt-LoRA brings parameter-efficient tuning close to full fine-tuning and surpasses it on some domains. Sentence-level labels outperform corpus-level ones, especially on large, noisy corpora. This gives resource-limited teams an affordable, domain-robust route to translation for low-resource languages.

Key points

  • The base model is NLLB-200, and the language direction is English→Irish. Domain adapters update only 1.39% of model parameters.
  • Dynamic routing at inference lets one base model plus small per-domain LoRA adapters replace several separately fine-tuned full models.
  • The study compares four setups: SemiAdapt-LoRA, plain LoRA, SemiAdapt-Full and full-model fine-tuning. It also contrasts corpus-level with sentence-level domain labelling.
  • The cited language resources include:
    • OPUS, Europarl and the EU Bookshop corpus
    • the Gaois English–Irish legislation corpus
    • Foclóir.ie example sentences
    • Irish State Examination Papers
    • LoResMT 2021 data
  • Code and training configurations are released at github.com/JoshMcGiff/SemiAdapt, including the NLLB-200 full fine-tuning baselines.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Topics: Machine translation

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/2gfkah2nq6uv

@inproceedings{mcgiff2026semiadapt,
  title = {{SemiAdapt: Semi-Supervised and Efficient LoRA-Based Domain Adaptation for Low-Resource Irish Machine Translation with Transformers}},
  author = {Mcgiff, Josh and Nikolov, Nikola S.},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/2gfkah2nq6uv},
  url = {https://doi.org/10.63317/2gfkah2nq6uv}
}

References

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

  1. Cormac Anderson, Sacha Beniamine, and Theodorus Fransen. 2024. Goidelex: A lexical resource for old irish. In Proceedings of the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA)@ LREC-COLING-2024, pages 1–10. find
  2. Mihael Arcan, Caoilfhionn Lane, Eoin Ó Droighneáin, and Paul Buitelaar. 2016. IRIS: English-Irish machine translation system. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 566–572, Portorož, Slovenia. European Language Resources Associatio… find
  3. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473. find our card
  4. Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Barry Haddow, Matthias Huck, Chris Hokamp, Philipp Koehn, Varvara Logacheva, Christof Monz, Matteo Negri, Matt Post, Carolina Scarton, Lucia Specia, and Marco Turchi. 2015. Findings of the 2015 workshop on statistical machine translation. In Proce… find our card
  5. Samuel Cahyawijaya, Genta Indra Winata, Bryan Wilie, Karissa Vincentio, Xiaohong Li, Adhiguna Kuncoro, Sebastian Ruder, Zhi Yuan Lim, Syafri Bahar, Masayu Khodra, Ayu Purwarianti, and Pascale Fung. 2021. IndoNLG: Benchmark and resources for evaluating Indonesian natural language generation. In Proce… find
  6. Sheila Castilho, Stephen Doherty, Federico Gaspari, and Joss Moorkens. 2018. Approaches to human and machine translation quality assessment. In Translation quality assessment: From principles to practice, pages 9–38. Springer. find
  7. Sheila Castilho, Joss Moorkens, Federico Gaspari, Iacer Calixto, John Tinsley, and Andy Way. 2017. Is neural machine translation the new state of the art? The Prague Bulletin of Mathematical Linguistics, (108). find
  8. Isaac Caswell, Theresa Breiner, Daan van Esch, and Ankur Bapna. 2020. Language ID in the wild: Unexpected challenges on the path to a thousand-language web text corpus. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6588–6608, Barcelona, Spain (Online). Inter… find our card
  9. Chenhui Chu, Raj Dabre, and Sadao Kurohashi. 2017a. An empirical comparison of domain adaptation methods for neural machine translation. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 385–391, Vancouver, Canada. Association… find
  10. Chenhui Chu, Raj Dabre, and Sadao Kurohashi. 2017b. An empirical comparison of domain adaptation methods for neural machine translation. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 385–391, Vancouver, Canada. Association… find
  11. Common Crawl. 2025. Common Crawl—Open Repository of Web Crawl Data. Accessed: 2025-07-29. find
  12. Marta R Costa-Jussà, James Cross, Onur Çelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, et al. 2022. No language left behind: Scaling human-centered machine translation. arXiv preprint arXiv:2207.04672. find
  13. Arne Defauw, Sara Szoc, Tom Vanallemeersch, Anna Bardadym, Joris Brabers, Frederic Everaert, Kim Scholte, Koen Van Winckel, and Joachim Van den Bogaert. 2019. Developing a neural machine translation system for irish. In Proceedings of the 2nd Workshop on Technologies for MT of Low Resource Languages… find
  14. Meghan Dowling, Sheila Castilho, Joss Moorkens, Teresa Lynn, and Andy Way. 2020. A human evaluation of English-Irish statistical and neural machine translation. In Proceedings of the 22nd Annual Conference of the European Association for Machine Translation, pages 431–440, Lisboa, Portugal. European… find
  15. Meghan Dowling, Teresa Lynn, Alberto Poncelas, and Andy Way. 2018. SMT versus NMT: Preliminary comparisons for Irish. In Proceedings of the AMTA 2018 Workshop on Technologies for MT of Low Resource Languages (LoResMT 2018), pages 12–20, Boston, MA. Association for Machine Translation in the Americas… find
  16. Marie Escribe. 2019. Human evaluation of neural machine translation: The case of deep learning. In Proceedings of the Human-Informed Translation and Interpreting Technology Workshop (HiT-IT 2019), pages 36–46. find
  17. Cristina España-Bonet and Marta R Costa-jussà. 2016. Hybrid machine translation overview. In Hybrid approaches to machine translation, pages 1–24. Springer. find
  18. Júlia Falcão, Claudia Borg, Nora Aranberri, and Kurt Abela. 2024. COMET for low-resource machine translation evaluation: A case study of English-Maltese and Spanish-Basque. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC… find
  19. Wenfeng Feng, Chuzhan Hao, Yuewei Zhang, Yu Han, and Hao Wang. 2024. Mixture-of-loras: An efficient multitask tuning method for large language models. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 1… find
  20. Markus Freitag and Yaser Al-Onaizan. 2016. Fast domain adaptation for neural machine translation. arXiv preprint arXiv:1612.06897. — [arXiv:1612.06897](https://arxiv.org/abs/1612.06897) find
  21. Yingbo Gao, Christian Herold, Zijian Yang, and Hermann Ney. 2022. Revisiting checkpoint averaging for neural machine translation. In Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022, pages 188–196, Online only. Association for Computational Linguistics. find
  22. Stig-Arne Grönroos, Sami Virpioja, and Mikko Kurimo. 2020. Transfer learning and subword sampling for asymmetric-resource one-to-many neural translation. Machine Translation, 34(4):251–286. find
  23. Tina Hickey. 2009. Code-switching and borrowing in irish 1. Journal of Sociolinguistics, 13(5):670– 688. find
  24. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2022. Lora: Low-rank adaptation of large language models. ICLR, 1(2):3. find
  25. Catherine Kobus, Josep Crego, and Jean Senellart. 2017. Domain control for neural machine translation. In Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017, pages 372–378, Varna, Bulgaria. INCOMA Ltd. find
  26. Julia Kreutzer, Isaac Caswell, Lisa Wang, Ahsan Wahab, Daan Van Esch, Nasanbayar Ulzii-Orshikh, Allahsera Tapo, Nishant Subramani, Artem Sokolov, Claytone Sikasote, et al. 2022. Quality at a glance: An audit of web-crawled multilingual datasets. Transactions of the Association for Computational Ling… find our card
  27. Séamus Lankford, Haithem Afli, Órla Ní Loinsigh, and Andy Way. 2022a. gaHealth: An English– Irish bilingual corpus of health data. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 6753–6758, Marseille, France. European Language Resources Association. find
  28. Séamus Lankford, Haithem Afli, and Andy Way. 2022b. Human evaluation of english–irish transformer-based nmt. Information, 13(7):309. find
  29. Seamus Lankford, Haithem Alfi, and Andy Way. 2021. Transformers for low-resource languages: Is féidir linn! In Proceedings of Machine Translation Summit XVIII: Research Track, pages 48–60, Virtual. Association for Machine Translation in the Americas. find
  30. Siobhán Ní Laoire. 2016. Irish-english code-switching: a sociolinguistic perspective. In Sociolinguistics in Ireland, pages 81–106. Springer. find
  31. Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020. BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In Proceedings of the 58th Annual Meeting of the… find our card
  32. Evelyn Kai-Yan Liu. 2022. Low-resource neural machine translation: A case study of Cantonese. In Proceedings of the Ninth Workshop on NLP for Similar Languages, Varieties and Dialects, pages 28–40, Gyeongju, Republic of Korea. Association for Computational Linguistics. find
  33. Ali Marashian, Enora Rice, Luke Gessler, Alexis Palmer, and Katharina von der Wense. 2025. From priest to doctor: Domain adaptation for low-resource neural machine translation. In Proceedings of the 31st International Conference on Computational Linguistics, pages 7087–7098, Abu Dhabi, UAE. Associat… find
  34. Nitika Mathur, Timothy Baldwin, and Trevor Cohn. 2020. Tangled up in BLEU: Reevaluating the evaluation of automatic machine translation evaluation metrics. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4984–4997, Online. Association for Computation… find our card
  35. Josh McGiff and Nikola S Nikolov. 2025. Overcoming data scarcity in generative language modelling for low-resource languages: A systematic review. arXiv preprint arXiv:2505.04531. find
  36. Meta AI. 2024. Scaling neural machine translation to 200 languages. Nature, 630(8018):841–846. find
  37. Kelechi Ogueji, Yuxin Zhu, and Jimmy Lin. 2021. Small data? no problem! exploring the viability of pretrained multilingual language models for low-resourced languages. In Proceedings of the 1st workshop on multilingual representation learning, pages 116–126. find our card
  38. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pages 311–318, Philadelphia, Pennsylvania, USA. Association for Computational… find our card
  39. Ricardo Rei, Craig Stewart, Ana C Farinha, and Alon Lavie. 2020. COMET: A neural framework for MT evaluation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2685–2702, Online. Association for Computational Linguistics. find our card
  40. Nathaniel Robinson, Perez Ogayo, David R. Mortensen, and Graham Neubig. 2023. Chat-GPT MT: Competitive for high- (but not low-) resource languages. In Proceedings of the Eighth Conference on Machine Translation, pages 392– 418, Singapore. Association for Computational Linguistics. find
  41. Emmanouil Stergiadis, Satendra Kumar, Fedor Kovalev, and Pavel Levin. 2021. Multi-domain adaptation in neural machine translation through multidimensional tagging. In Proceedings of Machine Translation Summit XVIII: Users and Providers Track, pages 396–420, Virtual. Association for Machine Translati… find
  42. Ashwani Tanwar and Prasenjit Majumder. 2020. Translating morphologically rich indian languages under zero-resource conditions. ACM Trans. Asian Low-Resour. Lang. Inf. Process., 19(6). find
  43. Yimin Tian, Bolin Zhang, Zhiying Tu, and Dianhui Chu. 2025. Adapters selector: Cross-domains and multi-tasks lora modules integration usage method. In Proceedings of the 31st International Conference on Computational Linguistics, pages 593–605. find
  44. Khanh-Tung Tran, Barry O’Sullivan, and Hoang Nguyen. 2024. Irish-based large language model with extreme low-resource settings in machine translation. In Proceedings of the Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024), pages 193–202. find
  45. Matej Ulčar and Marko Robnik-Šikonja. 2023. Sequence-to-sequence pretraining for a less-resourced slovenian language. Frontiers in Artificial Intelligence, 6:932519. find
  46. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, 30. find
  47. Jiayi Wang, David Ifeoluwa Adelani, Sweta Agrawal, Marek Masiak, Ricardo Rei, Eleftheria Briakou, Marine Carpuat, Xuanli He, Sofia Bourhim, Andiswa Bukula, Muhidin Mohamed, Temitayo Olatoye, Tosin Adewumi, Hamam Mokayed, Christine Mwase, Wangui Kimotho, Foutse Yuehgoh, Anuoluwapo Aremu, Jessica Ojo,… find
  48. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, Remi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lhoe… find our card
  49. Wilson Wongso, Ananto Joyoadikusumo, Brandon Scott Buana, and Derwin Suhartono. 2023. Many-to-many multilingual translation model for languages of indonesia. IEEE Access, 11:91385– 91397. find
  50. Sen Xu, Yi Zhou, Wei Wang, Jixin Min, Zhibin Yin, Yingwei Dai, Shixi Liu, Lianyu Pang, Yirong Chen, and Junlin Zhang. 2025. Tiny model, big logic: Diversity-driven optimization elicits large-model reasoning ability in vibethinker-1.5b. find
  51. Xuan Zhang, Navid Rajabi, Kevin Duh, and Philipp Koehn. 2023. Machine translation with large language models: Prompting, few-shot learning, and fine-tuning with qlora. In Proceedings of the Eighth Conference on Machine Translation, pages 468–481. find
  52. Vilém Zouhar, Pinzhen Chen, Tsz Kin Lam, Nikita Moghe, and Barry Haddow. 2024. Pitfalls and outlooks in using COMET. In Proceedings of the Ninth Conference on Machine Translation, pages 1272–1288, Miami, Florida, USA. Association for Computational Linguistics. 10. Language Resource References Foras… find
  53. Gaois research group. 2021. Gaois: Bilingual Corpus of English–Irish Legislation. Maintained by the Gaois research group, Fiontar & Scoil na Gaeilge, Dublin City University. find
  54. Koehn, Philipp. 2005. Europarl: A Parallel Corpus for Statistical Machine Translation. find
  55. Ojha, Atul Kr. and Liu, Chao-Hong and Kann, Katharina and Ortega, John and Shatam, Sheetal and Fransen, Theodorus. 2021. Findings of the LoResMT 2021 Shared Task on COVID and Sign Language for Low-resource Languages. Association for Machine Translation in the Americas. find
  56. Raivis Skadin , š, Jörg Tiedemann, Roberts Rozis, and Daiga Deksne. 2014. Billions of parallel words for free: Building and using the EU bookshop corpus. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14), pages 1850–1855, Reykjavik, Iceland. European… find
  57. State Examinations Commission. 2025. Irish State Examination Papers. Official bilingual examination materials used for research purposes. Publicly accessible, not redistributable. find
  58. Jörg Tiedemann. 2012. Parallel data, tools and interfaces in OPUS. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12), pages 2214–2218, Istanbul, Turkey. European Language Resources Association (ELRA). find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/mcgiff-2026-semiadapt-semi-supervised-efficient-lora/