Challenge: Existing mPLMs that handle non-transliterated data are not sufficient to train crosslingual models.
Approach: They propose a framework to transliterate related languages into a common script by exploiting existing mPLMs and their tokenizer without any training.
Outcome: The proposed framework can create strong baselines for data that is transliterated into a common script by exploiting an existing mPLM and its tokenizer without any training.

Similar Papers

Breaking the Script Barrier in Multilingual Pre-Trained Language Models with Transliteration-Based Post-Training Alignment (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent mPLMs have shown impressive performance on crosslingual transfer tasks . however, the performance is often hindered when a lowresource target language is written in a different script than the high-resource source language.
Approach: They propose a transliteration-based method to improve cross-lingual alignment between languages using diverse scripts.
Outcome: The proposed method outperforms the original model on Englishcentric transfer tasks up to 50%.
TransliCo: A Contrastive Learning Framework to Address the Script Barrier in Multilingual Pretrained Language Models (2024.acl-long)

Copied to clipboard

Challenge: The world’s more than 7000 languages are written in at least 293 scripts, which poses a difficulty for multilingual pretrained language models in learning crosslingual knowledge through lexical overlap.
Approach: They propose a framework that optimizes the Transliteration Contrastive Modeling objective to fine-tune an mPLM by contrasting sentences in its training data and transliterations in a unified script.
Outcome: The proposed model outperforms Glot500-m on zero-shot crosslingual transfer tasks while retaining uniformity across scripts.
ScriptMix: Mixing Scripts for Low-resource Language Parsing (2024.naacl-long)

Copied to clipboard

Challenge: Existing work has considered transliteration and vocabulary augmentation, but the consideration of combining the two has been lacking.
Approach: They propose a multilingual pretrained language model that combines two strengths and overcomes the hurdle of combining them.
Outcome: The proposed model improves POS accuracy by 14% and improves DEP LAS score by 5.6%.
Romanization-based Large-scale Adaptation of Multilingual Language Models (2023.findings-emnlp)

Copied to clipboard

Challenge: Large multilingual pretrained language models are limited by their vocabulary size and parameter budget.
Approach: They explore the potential of leveraging transliteration on a massive scale to improve performance for multilingual pretrained language models.
Outcome: The proposed transliteration tool outperforms other methods on low-resource languages.
LangSAMP: Language-Script Aware Multilingual Pretraining (2025.acl-long)

Copied to clipboard

Challenge: Recent multilingual pretrained language models often avoid using language embeddings, which places a significant burden on token representations to encode all language-specific information.
Approach: They propose a method that incorporates both language and script embeddings into the output of Transformer blocks before passing the final representations to the language modeling head for prediction.
Outcome: The proposed method outperforms the baseline model in zero-shot crosslingual transfer across diverse downstream tasks.
How Transliterations Improve Crosslingual Alignment (2025.coling-main)

Copied to clipboard

Challenge: Recent studies show that post-aligning multilingual pretrained language models improve crosslingual alignment, but it is unclear how and why this is achieved.
Approach: They propose to explicitly evaluate crosslingual alignment by adding transliterations to models using original and transliterated data.
Outcome: The proposed approach improves crosslingual alignment even for random sentences.
WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models (2022.naacl-main)

Copied to clipboard

Challenge: Existing methods to train large pretrained language models require more computational resources and are expensive to train in other languages.
Approach: They propose a method to transfer pretrained language models to new languages using subword-based tokenization and embeddings.
Outcome: The proposed method outperforms existing methods on low-resource languages and makes training large models more accessible and less damaging to the environment.
Enhancing Cross-Lingual Transfer through Reversible Transliteration: A Huffman-Based Approach for Low-Resource Languages (2025.acl-long)

Copied to clipboard

Challenge: Large language models demonstrate cross-lingual transfer capabilities, but these capabilities often fail to extend to low-resource languages, especially those utilizing non-Latin scripts.
Approach: They propose to combine character transliteration with Huffman coding to create a complete transliterations framework that can be extended to other low-resource languages.
Outcome: The proposed framework reduces storage requirements and improves accuracy and accuracy across multiple downstream tasks while maintaining performance on high-resource languages.
Take a Closer Look at Multilinguality! Improve Multilingual Pre-Training Using Monolingual Corpora Only (2023.findings-emnlp)

Copied to clipboard

Challenge: Recent studies have demonstrated remarkable cross-lingual capability of pre-trained language models . however, semantic alignments may be the reason behind such capability but remain under-explored.
Approach: They propose token-level and semantic-level code-switched masked language modeling to improve cross-lingual interactions over mono-mPLMs without parallel sentences.
Outcome: The proposed method outperforms mono-mPLMs on natural language understanding and unsupervised machine translation tasks.
OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining (2024.findings-naacl)

Copied to clipboard

Challenge: Existing methods to pretrain multilingual models are limited by the number of embedding parameters and the complexity of the model.
Approach: They propose a framework that initializes the embeddings of unseen subwords and can adapt a model to multiple languages.
Outcome: The proposed framework can adapt a pre-trained model to multiple languages efficiently and effectively.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations