Elamur Research⌕
☰
home / papers / 2026 / Interlinear Glosses as a Multilingual Pivot for Machine Translation: An Updated Study on Turkish with Restricted Resources

Interlinear Glosses as a Multilingual Pivot for Machine Translation: An Updated Study on Turkish with Restricted Resources

Summary

This study tests whether interlinear glosses can work as a bridge when translating a morphologically rich language into English with very little parallel data. Turkish stands in for truly under-resourced languages. The authors limit themselves to fewer than 5k Turkish–English sentence pairs, plus a morphological analyzer and a bilingual dictionary, tools that such languages might realistically have. They update the three-stage pipeline of Zhou et al. (2020). First, each Turkish word is split into a lemma and morphological tags, and the tags are mapped to Leipzig Glossing Rules. Next, the lemmas are swapped for English equivalents using the dictionary. Finally, a model turns the resulting pseudo-gloss into fluent English. For this last stage, they compare multilingual NMT trained on GlossLM subsets with three open-weight 7–8B LLMs. Pivoting through glosses outperforms direct translation when parallel data is scarce. However, results depend heavily on gloss quality, and lexical errors cause the most damage. This is relevant for endangered languages, where linguists often produce glossed text but rarely large parallel corpora. Code and evaluation data are publicly released.

Key points

  • Turkish–English data: SETIMES contains about 207k news sentence pairs. The authors also built SETIMES-S, a version simplified with GPT-4 to CEFR A1–A2 level with sentences of about 7–8 words. It has 2,000 training and 600 evaluation pairs, so its style is closer to IGT.
  • Multilingual IGT data: GlossLM contains about 450k instances in about 1,800 languages. The training subsets (Subset-60k, Subset-100k, Subset-150k) include every example from 23 Turkic languages (1,962 in total), with 1,300 Turkish training items.
  • Evaluation sets:
    • TR-GLM: 200 Turkish GlossLM sentences with gold glosses, manually corrected by a native speaker for OCR, lexical and grammatical errors.
    • TR-Morph-GLM: a silver version with automatic pseudo-glosses.
    • TR-SET600: 600 sentences from SETIMES-S.
  • Data-scaling experiments: Starting from Subset-100k, the authors add 600, 1.2k or 1.8k SETIMES-S pairs to measure the effect of in-domain parallel data.
  • Findings: Gloss-based pivoting beats direct translation under restricted resources, but translation is sensitive to gloss accuracy, especially lexical glosses. The extract did not include numeric scores, so none are reported here.

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 10.63317/4km7f5p8epxt

@inproceedings{ozer2026interlinear,
  title = {{Interlinear Glosses as a Multilingual Pivot for Machine Translation: An Updated Study on Turkish with Restricted Resources}},
  author = {Ozer, Volkan and Okabe, Shu and Fraser, Alexander},
  booktitle = {Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages},
  year = {2026},
  doi = {10.63317/4km7f5p8epxt},
  url = {https://doi.org/10.63317/4km7f5p8epxt}
}

References

56 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Rami Al-Rfou’, Bryan Perozzi, and Steven Skiena. 2013. Polyglot: Distributed word representations for multilingual NLP. In Proceedings of the Seventeenth Conference on Computational Natural Language Learning, pages 183–192, Sofia, Bulgaria. Association for Computational Linguistics. find our card
  2. Balthazar Bickel, Bernard. Comrie, and Martin Haspelmath. 2008. The Leipzig Glossing Rules: Conventions for interlinear morpheme-by-morpheme glosses. Leipzig: Max Planck Institute for Evolutionary Anthropology, Department of Linguistics. https://www.eva.mpg.de/lingua/ resources/glossing-rules.php. ↗
  3. Steven Bird and Edward Loper. 2004. NLTK: The natural language toolkit. In Proceedings of the ACL Interactive Poster and Demonstration Sessions, pages 214–217, Barcelona, Spain. Association for Computational Linguistics. find our card
  4. Çağrı Çöltekin. 2010. A freely available morphological analyzer for Turkish. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10), Valletta, Malta. European Language Resources Association (ELRA). find
  5. Çağrı Çöltekin. 2014. A set of open source tools for Turkish natural language processing. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14), pages 1079–1086, Reykjavik, Iceland. European Language Resources Association (ELRA). find
  6. Ryan Cotterell and Hinrich Schütze. 2015. Morphological word-embeddings. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1287–1292, Denver, Colorado. Association for Computational Linguistics. find
  7. Council of Europe. 2001. Common european framework of reference for languages: Learning, teaching, assessment. https://rm.coe.int/168045b15e. ↗
  8. Yiming Cui, Wanxiang Che, Shijin Wang, and Ting Liu. 2022. Lert: A linguistically-motivated pre-trained language model. find
  9. Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. 2023. QLoRA: Efficient finetuning of quantized LLMs. In Thirty-seventh Conference on Neural Information Processing Systems. find
  10. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,… find
  11. Daxiang Dong, Hua Wu, Wei He, Dianhai Yu, and Haifeng Wang. 2015. Multi-task learning for multiple language translation. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Lon… find our card
  12. Zi-Yi Dou and Graham Neubig. 2021. Word alignment by fine-tuning embeddings on parallel corpora. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 2112–2128, Online. Association for Computational Linguistics. find
  13. Orhan Firat, Kyunghyun Cho, and Yoshua Bengio. 2016. Multi-way, multilingual neural machine translation with a shared attention mechanism. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 866–875,… find our card
  14. Markus Freitag, Nitika Mathur, Daniel Deutsch, Chi-Kiu Lo, Eleftherios Avramidis, Ricardo Rei, Brian Thompson, Frederic Blain, Tom Kocmi, Jiayi Wang, David Ifeoluwa Adelani, Marianna Buchicchio, Chrysoula Zerva, and Alon Lavie. 2024. Are LLMs breaking MT metrics? results of the WMT24 metrics shared… find our card
  15. Xavier Garcia, Yamini Bansal, Colin Cherry, George Foster, Maxim Krikun, Melvin Johnson, and Orhan Firat. 2023. The unreasonable effectiveness of few-shot learning for machine translation. In Proceedings of the 40th International Conference on Machine Learning, ICML’23. JMLR.org. find
  16. Mercedes García-Martínez, Loïc Barrault, and Fethi Bougares. 2016. Factored neural machine translation architectures. In Proceedings of the 13th International Conference on Spoken Language Translation, Seattle, Washington D.C. International Workshop on Spoken Language Translation. find
  17. Dan Gillick, Cliff Brunk, Oriol Vinyals, and Amarnag Subramanya. 2016. Multilingual language processing from bytes. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1296–1306, San Diego, Californi… find
  18. Michael Ginn, Mans Hulden, and Alexis Palmer. 2024a. Can we teach language models to gloss endangered languages? In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 5861–5876, Miami, Florida, USA. Association for Computational Linguistics. find
  19. Michael Ginn, Sarah Moeller, Alexis Palmer, Anna Stacey, Garrett Nicolai, Mans Hulden, and Miikka Silfverberg. 2023. Findings of the SIGMOR-PHON 2023 shared task on interlinear glossing. In Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology,… find
  20. Michael Ginn, Lindia Tjuatja, Taiqi He, Enora Rice, Graham Neubig, Alexis Palmer, and Lori Levin. 2024b. GlossLM: A massively multilingual corpus and pretrained model for interlinear glossed text. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 12267–… find
  21. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, Arun Rao,… find
  22. Nuno M. Guerreiro, Ricardo Rei, Daan van Stigt, Luisa Coheur, Pierre Colombo, and André F. T. Martins. 2024. xCOMET: Transparent machine translation evaluation through fine-grained error detection. Transactions of the Association for Computational Linguistics, 12:979–995. find our card
  23. Nizar Habash and Fatiha Sadat. 2006. Arabic preprocessing schemes for statistical machine translation. In Proceedings of the Human Language Technology Conference of the NAACL, Companion Volume: Short Papers, pages 49–52, New York City, USA. Association for Computational Linguistics. find our card
  24. Amr Hendy, Mohamed Abdelrehim, Amr Sharaf, Vikas Raunak, Mohamed Gabr, Hitokazu Matsushita, Young Jin Kim, Mohamed Afify, and Hany Hassan Awadalla. 2023. How good are gpt models at machine translation? a comprehensive evaluation. find
  25. Melvin Johnson, Mike Schuster, Quoc V. Le, Maxim Krikun, Yonghui Wu, Zhifeng Chen, Nikhil Thorat, Fernanda Viégas, Martin Wattenberg, Greg Corrado, Macduff Hughes, and Jeffrey Dean. 2017. Google’s multilingual neural machine translation system: Enabling zero-shot translation. Transactions of the Ass… find
  26. Ayla Kayabaş, Helmut Schmid, Ali E. Topcu, and Özlem Kılıç. 2019. Trmor: a finite-state-based morphological analyzer for turkish. Turkish Journal of Electrical Engineering & Computer Sciences. find
  27. Guillaume Klein, Yoon Kim, Yuntian Deng, Vincent Nguyen, Jean Senellart, and Alexander Rush. 2018. OpenNMT: Neural machine translation toolkit. In Proceedings of the 13th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track), pages 177–184, Boston, MA. Asso… find
  28. Philipp Koehn and Hieu Hoang. 2007. Factored translation models. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pages 868–876, Prague, Czech Republic. Association for Computational Linguistics… find our card
  29. Philipp Koehn and Rebecca Knowles. 2017. Six challenges for neural machine translation. In Proceedings of the First Workshop on Neural Machine Translation, pages 28–39, Vancouver. Association for Computational Linguistics. find
  30. Young-Suk Lee. 2004. Morphological analysis for statistical machine translation. In Proceedings of HLT-NAACL 2004: Short Papers, pages 57– 60, Boston, Massachusetts, USA. Association for Computational Linguistics. find
  31. Wang Ling, Isabel Trancoso, Chris Dyer, and Alan W Black. 2015. Character-based neural machine translation. find our card
  32. Toan Q. Nguyen and David Chiang. 2017. Transfer learning across low-resource, related languages for neural machine translation. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 296–301, Taipei, Taiwan. Asian Federation of Natu… find our card
  33. Sebastian Nordhoff and Thomas Krämer. 2022. IMTVault: Extracting and enriching low-resource language interlinear glossed text from grammatical descriptions and typological survey articles. In Proceedings of the 8th Workshop on Linked Data in Linguistics within the 13th Language Resources and Evaluat… find
  34. OpenAI, Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, Red Avila, Igor Babuschkin, Suchir Balaji, Valerie Balcom, Paul Baltescu, Haiming Bao, Mohammad Bavarian, Jeff Belgum, Irwan Bello, Ja… find our card
  35. Adnan Öztürel, Tolga Kayadelen, and Işın Demirşahin. 2019. A syntactically expressive morphological analyzer for turkish. In Proceedings of the 14th International Conference on Finite-State Methods and Natural Language Processing, pages 65–75, Dresden, Germany. Association for Computational Linguist… find
  36. 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
  37. Maja Popović. 2015. chrF: character n-gram Fscore for automatic MT evaluation. In Proceedings of the Tenth Workshop on Statistical Machine Translation, pages 392–395, Lisbon, Portugal. Association for Computational Linguistics. find
  38. Matt Post. 2018. A call for clarity in reporting BLEU scores. In Proceedings of the Third Conference on Machine Translation: Research Papers, pages 186–191, Brussels, Belgium. Association for Computational Linguistics. find our card
  39. Qwen, :, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, Kai Dang, Keming Lu, Keqin Bao, Kexin Yang, Le Yu, Mei Li, Mingfeng… find
  40. Rita Ramos, Everlyn Asiko Chimoto, Maartje Ter Hoeve, and Natalie Schluter. 2025. GrammaMT: Improving machine translation with grammar-informed in-context learning. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 29920–29940,… find our card
  41. Maciej Rapacz and Aleksander Smywiński-Pohl. 2025. Low-resource interlinear translation: Morphology-enhanced neural models for Ancient Greek. In Proceedings of the First Workshop on Language Models for Low-Resource Languages, pages 145–165, Abu Dhabi, United Arab Emirates. Association for Computatio… find
  42. 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
  43. Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016. Neural machine translation of rare words with subword units. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1715–1725, Berlin, Germany. Association for Computational Lin… find
  44. Felix Stahlberg, Eva Hasler, Aurelien Waite, and Bill Byrne. 2016. Syntactically guided neural machine translation. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 299–305, Berlin, Germany. Association for Computational Lingu… find
  45. John Sylak-Glassman, Christo Kirov, David Yarowsky, and Roger Que. 2015. A language-independent feature schema for inflectional morphology. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Proces… find
  46. Garrett Tanzer, Mirac Suzgun, Eline Visser, Dan Jurafsky, and Luke Melas-Kyriazi. 2024. A benchmark for learning to translate a new language from one grammar book. find
  47. Xinyi Wang, Sebastian Ruder, and Graham Neubig. 2022. Expanding pretrained models to thousands more languages via lexicon-based adaptation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 863–877, Dublin, Ireland. Association… find
  48. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jing Zhou, Jin… find our card
  49. Biao Zhang, Barry Haddow, and Alexandra Birch. 2023. Prompting large language model for machine translation: a case study. In Proceedings of the 40th International Conference on Machine Learning, ICML’23. JMLR.org. find our card
  50. Kexun Zhang, Yee Choi, Zhenqiao Song, Taiqi He, William Yang Wang, and Lei Li. 2024. Hire a linguist!: Learning endangered languages in LLMs with in-context linguistic descriptions. In Findings of the Association for Computational Linguistics: ACL 2024, pages 15654–15669, Bangkok, Thailand. Associat… find
  51. Zhong Zhou, Lori Levin, David R. Mortensen, and Alex Waibel. 2020. Using interlinear glosses as pivot in low-resource multilingual machine translation. find
  52. Barret Zoph, Deniz Yuret, Jonathan May, and Kevin Knight. 2016. Transfer learning for low-resource neural machine translation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1568–1575, Austin, Texas. Association for Computational Linguistics. 11. find
  53. Language Resource References Ginn, Michael and Tjuatja, Lindia and He, Taiqi and Rice, Enora and Neubig, Graham and Palmer, Alexis and Levin, Lori. 2024. GlossLM: A Massively Multilingual Corpus and Pre-trained Model for Interlinear Glossed Text. Association for Computational Linguistics. PID https:… find
  54. Lewis, William D. and Xia, Fei. 2010. Developing ODIN: A Multilingual Repository of Annotated Language Data for Hundreds of the World’s Languages. PID http://depts.washington.edu/uwcl/odin/. ↗
  55. Nordhoff, Sebastian and Krämer, Thomas. 2022. IMTVault: Extracting and Enriching Low-resource Language Interlinear Glossed Text from Grammatical Descriptions and Typological Survey Articles. European Language Resources Association. PID https://imtvault.org/?languageiso6393filter=tur. ↗
  56. Tiedemann, Jörg. 2012. Parallel Data, Tools and Interfaces in OPUS. European Language Resources Association (ELRA). PID https://opus.nlpl.eu/datasets/SETIMES?pair=en&tr. ↗

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/ozer-2026-interlinear-glosses-as-multilingual-pivot/