Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

TransMI: A Framework to Create Strong Baselines from Multilingual Pretrained Language Models for Transliterated Data (2405.09913v2)

Published 16 May 2024 in cs.CL

Abstract: Transliterating related languages that use different scripts into a common script is effective for improving crosslingual transfer in downstream tasks. However, this methodology often makes pretraining a model from scratch unavoidable, as transliteration brings about new subwords not covered in existing multilingual pretrained LLMs (mPLMs). This is undesirable because it requires a large computation budget. A more promising way is to make full use of available mPLMs. To this end, this paper proposes a simple but effective framework: Transliterate-Merge-Initialize (TransMI). TransMI can create strong baselines for data that is transliterated into a common script by exploiting an existing mPLM and its tokenizer without any training. TransMI has three stages: (a) transliterate the vocabulary of an mPLM into a common script; (b) merge the new vocabulary with the original vocabulary; and (c) initialize the embeddings of the new subwords. We apply TransMI to three strong recent mPLMs. Our experiments demonstrate that TransMI not only preserves the mPLM's ability to handle non-transliterated data, but also enables it to effectively process transliterated data, thereby facilitating crosslingual transfer across scripts. The results show consistent improvements of 3% to 34% for different mPLMs and tasks. We make our code and models publicly available at \url{https://github.com/cisnlp/TransMI}.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. SIB-200: A simple, inclusive, and big evaluation dataset for topic classification in 200+ languages and dialects. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 226–245, St. Julian’s, Malta. Association for Computational Linguistics.
  2. Adapting pre-trained language models to African languages via multilingual adaptive fine-tuning. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4336–4349, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
  3. Chantal Amrhein and Rico Sennrich. 2020. On Romanization for model transfer between scripts in neural machine translation. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2461–2469, Online. Association for Computational Linguistics.
  4. On the cross-lingual transferability of monolingual representations. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4623–4637, Online. Association for Computational Linguistics.
  5. Mikel Artetxe and Holger Schwenk. 2019. Massively multilingual sentence embeddings for zero-shot cross-lingual transfer and beyond. Transactions of the Association for Computational Linguistics, 7:597–610.
  6. Unsupervised cross-lingual representation learning at scale. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8440–8451, Online. Association for Computational Linguistics.
  7. Universal Dependencies. Computational Linguistics, 47(2):255–308.
  8. Maximum likelihood from incomplete data via the em algorithm. Journal of the royal statistical society: series B (methodological), 39(1):1–22.
  9. 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, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics.
  10. Role of Language Relatedness in Multilingual Fine-tuning of Language Models: A Case Study in Indo-Aryan Languages. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8584–8595, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
  11. Philip Gage. 1994. A new algorithm for data compression. The C Users Journal, 12(2):23–38.
  12. Mozhdeh Gheini and Jonathan May. 2019. A universal parent model for low-resource neural machine translation transfer. arXiv preprint arXiv:1909.06516.
  13. Efficient neural machine translation for low-resource languages via exploiting related languages. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 162–168, Online. Association for Computational Linguistics.
  14. A survey on recent approaches for natural language processing in low-resource scenarios. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2545–2568, Online. Association for Computational Linguistics.
  15. Out-of-the-box universal Romanization tool uroman. In Proceedings of ACL 2018, System Demonstrations, pages 13–18, Melbourne, Australia. Association for Computational Linguistics.
  16. An embarrassingly simple method to mitigate undesirable properties of pretrained language model tokenizers. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 385–393, Dublin, Ireland. Association for Computational Linguistics.
  17. Glot500: Scaling multilingual corpora and language models to 500 languages. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1082–1117, Toronto, Canada. Association for Computational Linguistics.
  18. SimAlign: High quality word alignments without parallel training data using static and contextualized embeddings. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 1627–1643, Online. Association for Computational Linguistics.
  19. Vocabulary replacement in SentencePiece for domain adaptation. In Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation, pages 645–652, Hong Kong, China. Association for Computational Linguistics.
  20. Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings.
  21. Taku Kudo. 2018. Subword regularization: Improving neural network translation models with multiple subword candidates. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 66–75, Melbourne, Australia. Association for Computational Linguistics.
  22. Taku Kudo and John Richardson. 2018. SentencePiece: A simple and language independent subword tokenizer and detokenizer for neural text processing. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 66–71, Brussels, Belgium. Association for Computational Linguistics.
  23. Vocabulary modifications for domain-adaptive pretraining of clinical language models. In HEALTHINF, pages 180–188.
  24. Mala-500: Massive language adaptation of large language models. arXiv preprint arXiv:2401.13303.
  25. Choosing transfer languages for cross-lingual learning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3125–3135, Florence, Italy. Association for Computational Linguistics.
  26. Task-adaptive tokenization: Enhancing long-form text generation efficacy in mental health and beyond. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 15264–15281, Singapore. Association for Computational Linguistics.
  27. Ofa: A framework of initializing unseen subword embeddings for efficient large-scale multilingual continued pretraining. arXiv preprint arXiv:2311.08849.
  28. Translico: A contrastive learning framework to address the script barrier in multilingual pretrained language models. arXiv preprint arXiv:2401.06620.
  29. Zihan Liu. 2022. Effective Transfer Learning for Low-Resource Natural Language Understanding. Hong Kong University of Science and Technology (Hong Kong).
  30. Taxi1500: A multilingual dataset for text classification in 1500 languages. arXiv preprint arXiv:2305.08487.
  31. Low-resource languages: A review of past work and future challenges. arXiv preprint arXiv:2006.07264.
  32. Does transliteration help multilingual language modeling? In Findings of the Association for Computational Linguistics: EACL 2023, pages 670–685, Dubrovnik, Croatia. Association for Computational Linguistics.
  33. When being unseen from mBERT is just the beginning: Handling new languages with multilingual language models. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 448–462, Online. Association for Computational Linguistics.
  34. Cross-lingual name tagging and linking for 282 languages. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1946–1958, Vancouver, Canada. Association for Computational Linguistics.
  35. UNKs everywhere: Adapting multilingual language models to new scripts. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10186–10203, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
  36. How multilingual is multilingual BERT? In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4996–5001, Florence, Italy. Association for Computational Linguistics.
  37. Romanization-based large-scale adaptation of multilingual language models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 7996–8005, Singapore. Association for Computational Linguistics.
  38. Efficient domain adaptation of language models via adaptive tokenization. In Proceedings of the Second Workshop on Simple and Efficient Natural Language Processing, pages 155–165, Virtual. Association for Computational Linguistics.
  39. Mike Schuster and Kaisuke Nakajima. 2012. Japanese and korean voice search. In 2012 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2012, Kyoto, Japan, March 25-30, 2012, pages 5149–5152. IEEE.
  40. 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 Linguistics.
  41. The conversion of scripts, its nature, history, and utilization.
  42. Shijie Wu and Mark Dredze. 2019. Beto, bentz, becas: The surprising cross-lingual effectiveness of BERT. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 833–844, Hong Kong, China. Association for Computational Linguistics.
  43. Google’s neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144.
  44. 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.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Yihong Liu (25 papers)
  2. Chunlan Ma (20 papers)
  3. Haotian Ye (39 papers)
  4. Hinrich Schütze (250 papers)
Citations (3)
View on Semantic Scholar
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets