BamiBERT: A New BERT-based Language Model for Vietnamese

• URL: http://arxiv.org/abs/2607.02259v1
• Date: Thu, 02 Jul 2026 14:46:54 GMT
• Title: BamiBERT: A New BERT-based Language Model for Vietnamese
• Abstract summary: We introduce BamiBERT, a new BERT-based pre-trained language model for Vietnamese.<n>BamiBERT supports an extended context length of up to 2048 tokens and operates directly on raw input.<n>It achieves the best score on 11 of 15 metrics and the second-best on 3 others.
• Score: 15.256768347493832
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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

Related papers

• Omnilingual SONAR: Cross-Lingual and Cross-Modal Sentence Embeddings Bridging Massively Multilingual Text and Speech [61.759910921200834]
  Cross-lingual sentence encoders typically cover only a few hundred languages.<n>We introduce OmniSONAR, a new family of omnilingual, cross-lingual and cross-language sentence embedding models.
  arXiv  Detail & Related papers  (2026-03-17T14:47:35Z)
• mmBERT: A Modern Multilingual Encoder with Annealed Language Learning [57.58071656545661]
  mmBERT is an encoder-only language model pretrained on 3T tokens of multilingual text.<n>We add over 1700 low-resource languages to the data mix only during the decay phase.<n>We show that mmBERT significantly outperforms the previous generation of models on classification and retrieval tasks.
  arXiv  Detail & Related papers  (2025-09-08T17:08:42Z)
• Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval [49.1574468325115]
  We introduce Amharic-specific dense retrieval models based on pre-trained Amharic BERT and RoBERTa backbones.<n>Our proposed RoBERTa-Base-Amharic-Embed model (110M parameters) achieves a 17.6% relative improvement in MRR@10.<n>More compact variants, such as RoBERTa-Medium-Amharic-Embed (42M) remain competitive while being over 13x smaller.
  arXiv  Detail & Related papers  (2025-05-25T23:06:20Z)
• MaiBaam: A Multi-Dialectal Bavarian Universal Dependency Treebank [56.810282574817414]
  We present the first multi-dialect Bavarian treebank (MaiBaam) manually annotated with part-of-speech and syntactic dependency information in Universal Dependencies (UD) We highlight the morphosyntactic differences between the closely-related Bavarian and German and showcase the rich variability of speakers' orthographies. Our corpus includes 15k tokens, covering dialects from all Bavarian-speaking areas spanning three countries.
  arXiv  Detail & Related papers  (2024-03-15T13:33:10Z)
• ViSoBERT: A Pre-Trained Language Model for Vietnamese Social Media Text Processing [1.1765925931670576]
  We present the first monolingual pre-trained language model for Vietnamese social media texts, ViSoBERT. Our experiments demonstrate that ViSoBERT, with far fewer parameters, surpasses the previous state-of-the-art models on multiple Vietnamese social media tasks.
  arXiv  Detail & Related papers  (2023-10-17T11:34:50Z)
• ViDeBERTa: A powerful pre-trained language model for Vietnamese [10.000783498978604]
  This paper presents ViDeBERTa, a new pre-trained monolingual language model for Vietnamese. Three versions - ViDeBERTa_xsmall, ViDeBERTa_base, and ViDeBERTa_large - are pre-trained on a large-scale corpus of high-quality and diverse Vietnamese texts. We fine-tune and evaluate our model on three important natural language downstream tasks, Part-of-speech tagging, Named-entity recognition, and Question answering.
  arXiv  Detail & Related papers  (2023-01-25T07:26:54Z)
• Tencent AI Lab - Shanghai Jiao Tong University Low-Resource Translation System for the WMT22 Translation Task [49.916963624249355]
  This paper describes Tencent AI Lab - Shanghai Jiao Tong University (TAL-SJTU) Low-Resource Translation systems for the WMT22 shared task. We participate in the general translation task on English$Leftrightarrow$Livonian. Our system is based on M2M100 with novel techniques that adapt it to the target language pair.
  arXiv  Detail & Related papers  (2022-10-17T04:34:09Z)
• FBERT: A Neural Transformer for Identifying Offensive Content [67.12838911384024]
  fBERT is a BERT model retrained on SOLID, the largest English offensive language identification corpus available with over $1.4$ million offensive instances. We evaluate fBERT's performance on identifying offensive content on multiple English datasets and we test several thresholds for selecting instances from SOLID. The fBERT model will be made freely available to the community.
  arXiv  Detail & Related papers  (2021-09-10T19:19:26Z)
• COVID-19 Named Entity Recognition for Vietnamese [6.17059264011429]
  We present the first manually-annotated COVID-19 domain-specific dataset for Vietnamese. Our dataset is annotated for the named entity recognition task with newly-defined entity types. Our dataset also contains the largest number of entities compared to existing Vietnamese NER datasets.
  arXiv  Detail & Related papers  (2021-04-08T16:35:34Z)
• A Pilot Study of Text-to-SQL Semantic Parsing for Vietnamese [11.782566169354725]
  We present the first public large-scale Text-to-resource semantic parsing dataset for Vietnamese. We find that automatic Vietnamese word segmentation improves the parsing results of both baselines. PhoBERT for Vietnamese helps produce higher performances than the recent best multilingual language model XLM-R.
  arXiv  Detail & Related papers  (2020-10-05T09:54:51Z)
• PhoBERT: Pre-trained language models for Vietnamese [11.685916685552982]
  We present PhoBERT, the first public large-scale monolingual language models pre-trained for Vietnamese. Experimental results show that PhoBERT consistently outperforms the recent best pre-trained multilingual model XLM-R. We release PhoBERT to facilitate future research and downstream applications for Vietnamese NLP.
  arXiv  Detail & Related papers  (2020-03-02T10:21:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.