mlsanityData to 7 Oct 2026

Cross-Lingual Transfer for Machine Translation in Turkic Languages

arXiv 2607.29355 ↗First posted 31 Jul 2026cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Cross-lingual transfer is central to low-resource machine translation, but its behavior within closely related language families remains insufficiently characterized. We study transfer among five Turkic languages; Turkish, Azerbaijani, Uzbek, Kazakh, and Kyrgyz; using pairwise transfer matrices. In this setting, each model is fine-tuned with one transfer source and evaluated on a different transfer target while the translation target remains the same. Across mT5 experiments, we find that transfer is strongest between closely related Turkic pairs, especially Turkish-Azerbaijani and Kazakh-Kyrgyz. We also show that transfer direction matters, and that the same transfer source-transfer target pair can behave differently when the translation target changes. Latinization improves BLEU and chrF in several script-mismatched settings, but its effect is not uniform across metrics. Additional analyses show that transfer sources are mostly stable across different datasets and model settings.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 42 of its 59 references that are in the map. First posted on arXiv 31 Jul 2026.

Builds on

42 of 59 references.

References · 42

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  4. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  5. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  6. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,813
  7. 2016Enriching Word Vectors with Subword Informationcited by 1,578
  8. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
  9. 2020COMET: A Neural Framework for MT Evaluationcited by 1,024
  10. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  11. 2020Beyond English-Centric Multilingual Machine Translationcited by 559
  12. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 467
30 more
  1. 2018Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyondcited by 434
  2. 2023Large Language Models Are State-of-the-Art Evaluators of Translation Qualitycited by 416
  3. 2017Six Challenges for Neural Machine Translationcited by 334
  4. 2022CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Taskcited by 205
  5. 2023MADLAD-400: A Multilingual And Document-Level Large Audited Datasetcited by 180
  6. 2022Towards a Cleaner Document-Oriented Multilingual Crawled Corpuscited by 143
  7. 2023GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4cited by 143
  8. 2020The Tatoeba Translation Challenge -- Realistic Data Sets for Low Resource and Multilingual MTcited by 127
  9. 2017Transfer Learning across Low-Resource, Related Languages for Neural Machine Translationcited by 58
  10. 2018Trivial Transfer Learning for Low-Resource Neural Machine Translationcited by 47
  11. 2021Revisiting the Primacy of English in Zero-shot Cross-lingual Transfercited by 47
  12. 2022Large-Scale Hate Speech Detection with Cross-Domain Transfercited by 39
  13. 2019Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languagescited by 36
  14. 2024Breaking the Curse of Multilinguality with Cross-lingual Expert Language Modelscited by 36
  15. 2021A Large-Scale Study of Machine Translation in the Turkic Languagescited by 21
  16. 2023Romanization-based Large-scale Adaptation of Multilingual Language Modelscited by 21
  17. 2025ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilingualitycited by 19
  18. 2023Viewing Knowledge Transfer in Multilingual Machine Translation Through a Representational Lenscited by 15
  19. 2021Alternative Input Signals Ease Transfer in Multilingual Machine Translationcited by 14
  20. 2025Scaling Low-Resource MT via Synthetic Data Generation with LLMscited by 14
  21. 2019Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translationcited by 11
  22. 2025Conditions for Catastrophic Forgetting in Multilingual Translationcited by 10
  23. 2021Extremely low-resource machine translation for closely related languagescited by 7
  24. 2022Very Low Resource Sentence Alignment: Luhya and Swahilicited by 6
  25. 2020Exploring Benefits of Transfer Learning in Neural Machine Translationcited by 5
  26. 2024KazParC: Kazakh Parallel Corpus for Machine Translationcited by 5
  27. 2025Interference Matrix: Quantifying Cross-Lingual Interference in Transformer Encoderscited by 3
  28. 2024Disentangling the Roles of Target-Side Transfer and Regularization in Multilingual Machine Translationcited by 2
  29. 2023Improving Polish to English Neural Machine Translation with Transfer Learning: Effects of Data Volume and Language Similaritycited by 1
  30. 2023Simple and Effective Input Reformulations for Translationcited by 1

Built on by

Not cited yet.