# BamiBERT: A New BERT-based Language Model for Vietnamese

arXiv: https://arxiv.org/abs/2607.02259 · HTML: https://mlsanity.com/paper/2607.02259/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 24 references that are in the map.
- First posted on arXiv 2 Jul 2026.

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://mlsanity.com/paper/2412.13663/) (2024)
- [PhoBERT: Pre-trained language models for Vietnamese](https://mlsanity.com/paper/2003.00744/) (2020)
- [VnCoreNLP: A Vietnamese Natural Language Processing Toolkit](https://mlsanity.com/paper/1801.01331/) (2018)
- [Improving Sequence Tagging for Vietnamese Text Using Transformer-based Neural Models](https://mlsanity.com/paper/2006.15994/) (2020)
- [A Fast and Accurate Vietnamese Word Segmenter](https://mlsanity.com/paper/1709.06307/) (2017)
- [COVID-19 Named Entity Recognition for Vietnamese](https://mlsanity.com/paper/2104.03879/) (2021)
- [SA2SL: From Aspect-Based Sentiment Analysis to Social Listening System for Business Intelligence](https://mlsanity.com/paper/2105.15079/) (2021)
- [ViDeBERTa: A powerful pre-trained language model for Vietnamese](https://mlsanity.com/paper/2301.10439/) (2023)
- [ViSoBERT: A Pre-Trained Language Model for Vietnamese Social Media Text Processing](https://mlsanity.com/paper/2310.11166/) (2023)

## Abstract (arXiv)

In this paper, we introduce BamiBERT, a new BERT-based pre-trained language model for Vietnamese that addresses key limitations of PhoBERT -- the current de facto Vietnamese text encoder. Trained from scratch on a 129GB corpus of general-domain Vietnamese text for 20 epochs, BamiBERT supports an extended context length of up to 2048 tokens and operates directly on raw input, eliminating the need for external word segmentation. Across 8 Vietnamese benchmarks, it achieves the best score on 11 of 15 metrics and the second-best on 3 others, setting a new state of the art among "base"-sized Vietnamese encoders and demonstrating strong cross-domain generalization. We release BamiBERT at: https://huggingface.co/Qualcomm-AI-Research/BamiBERT