MaiBERT: A Pre-training Corpus and Language Model for Low-Resourced Maithili Language
Abstract
Natural Language Understanding (NLU) for low-resource languages remains a major challenge in NLP due to the scarcity of high-quality data and language-specific models. Maithili, despite being spoken by millions, lacks adequate computational resources, limiting its inclusion in digital and AI-driven applications. To address this gap, we introducemaiBERT, a BERT-based language model pre-trained specifically for Maithili using the Masked Language Modeling (MLM) technique. Our model is trained on a newly constructed Maithili corpus and evaluated through a news classification task. In our experiments, maiBERT achieved an accuracy of 87.02%, outperforming existing regional models like NepBERTa and HindiBERT, with a 0.13% overall accuracy gain and 5-7% improvement across various classes. We have open-sourced maiBERT on Hugging Face enabling further fine-tuning for downstream tasks such as sentiment analysis and Named Entity Recognition (NER).
Cite
@article{arxiv.2509.15048,
title = {MaiBERT: A Pre-training Corpus and Language Model for Low-Resourced Maithili Language},
author = {Sumit Yadav and Raju Kumar Yadav and Utsav Maskey and Gautam Siddharth Kashyap and Ganesh Gautam and Usman Naseem},
journal= {arXiv preprint arXiv:2509.15048},
year = {2026}
}
Comments
Accepted at EACL LoResLM 2026