# Effective vocabulary expansion of multilingual language models for extremely low-resource languages

arXiv: https://arxiv.org/abs/2602.09388 · HTML: https://mlsanity.com/paper/2602.09388/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 35 references that are in the map.
- First posted on arXiv 10 Feb 2026.

## Builds on (most cited first, 28 of 28)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization](https://mlsanity.com/paper/2003.11080/) (2020)
- [Beyond English-Centric Multilingual Machine Translation](https://mlsanity.com/paper/2010.11125/) (2020)
- [Learning multiple visual domains with residual adapters](https://mlsanity.com/paper/1705.08045/) (2017)
- [Word Translation Without Parallel Data](https://mlsanity.com/paper/1710.04087/) (2017)
- [Are All Languages Created Equal in Multilingual BERT?](https://mlsanity.com/paper/2005.09093/) (2020)
- [A Survey Of Cross-lingual Word Embedding Models](https://mlsanity.com/paper/1706.04902/) (2017)
- [Unicoder: A Universal Language Encoder by Pre-training with Multiple Cross-lingual Tasks](https://mlsanity.com/paper/1909.00964/) (2019)
- [75 Languages, 1 Model: Parsing Universal Dependencies Universally](https://mlsanity.com/paper/1904.02099/) (2019)
- [WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models](https://mlsanity.com/paper/2112.06598/) (2021)
- [Extending Multilingual BERT to Low-Resource Languages](https://mlsanity.com/paper/2004.13640/) (2020)
- [ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual Corpora](https://mlsanity.com/paper/2012.15674/) (2020)
- [As Good as New. How to Successfully Recycle English GPT-2 to Make Models for Other Languages](https://mlsanity.com/paper/2012.05628/) (2020)
- [How to Adapt Your Pretrained Multilingual Model to 1600 Languages](https://mlsanity.com/paper/2106.02124/) (2021)
- [A Primer on Pretrained Multilingual Language Models](https://mlsanity.com/paper/2107.00676/) (2021)
- [Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptation](https://mlsanity.com/paper/2203.09435/) (2022)
- [From English To Foreign Languages: Transferring Pre-trained Language Models](https://mlsanity.com/paper/2002.07306/) (2020)
- [Are All Good Word Vector Spaces Isomorphic?](https://mlsanity.com/paper/2004.04070/) (2020)
- [Load What You Need: Smaller Versions of Multilingual BERT](https://mlsanity.com/paper/2010.05609/) (2020)
- [MultiFiT: Efficient Multi-lingual Language Model Fine-tuning](https://mlsanity.com/paper/1909.04761/) (2019)
- [Improving Pre-Trained Multilingual Models with Vocabulary Expansion](https://mlsanity.com/paper/1909.12440/) (2019)
- [Massively Multilingual Word Embeddings](https://mlsanity.com/paper/1602.01925/) (2016)
- [Learning Multilingual Word Embeddings in Latent Metric Space: A Geometric Approach](https://mlsanity.com/paper/1808.08773/) (2018)
- [Subword Mapping and Anchoring across Languages](https://mlsanity.com/paper/2109.04556/) (2021)

## Abstract (arXiv)

Multilingual pre-trained language models(mPLMs) offer significant benefits for many low-resource languages. To further expand the range of languages these models can support, many works focus on continued pre-training of these models. However, few works address how to extend mPLMs to low-resource languages that were previously unsupported. To tackle this issue, we expand the model's vocabulary using a target language corpus. We then screen out a subset from the model's original vocabulary, which is biased towards representing the source language(e.g. English), and utilize bilingual dictionaries to initialize the representations of the expanded vocabulary. Subsequently, we continue to pre-train the mPLMs using the target language corpus, based on the representations of these expanded vocabulary. Experimental results show that our proposed method outperforms the baseline, which uses randomly initialized expanded vocabulary for continued pre-training, in POS tagging and NER tasks, achieving improvements by 0.54% and 2.60%, respectively. Furthermore, our method demonstrates high robustness in selecting the training corpora, and the models' performance on the source language does not degrade after continued pre-training.