Benchmarking BERT-based Models for Sentence-level Topic Classification in Nepali Language
Abstract
Transformer-based models such as BERT have significantly advanced Natural Language Processing (NLP) across many languages. However, Nepali, a low-resource language written in Devanagari script, remains relatively underexplored. This study benchmarks multilingual, Indic, Hindi, and Nepali BERT variants to evaluate their effectiveness in Nepali topic classification. Ten pre-trained models, including mBERT, XLM-R, MuRIL, DevBERT, HindiBERT, IndicBERT, and NepBERTa, were fine-tuned and tested on the balanced Nepali dataset containing 25,006 sentences across five conceptual domains and the performance was evaluated using accuracy, weighted precision, recall, F1-score, and AUROC metrics. The results reveal that Indic models, particularly MuRIL-large, achieved the highest F1-score of 90.60%, outperforming multilingual and monolingual models. NepBERTa also performed competitively with an F1-score of 88.26%. Overall, these findings establish a robust baseline for future document-level classification and broader Nepali NLP applications.
Cite
@article{arxiv.2602.23940,
title = {Benchmarking BERT-based Models for Sentence-level Topic Classification in Nepali Language},
author = {Nischal Karki and Bipesh Subedi and Prakash Poudyal and Rupak Raj Ghimire and Bal Krishna Bal},
journal= {arXiv preprint arXiv:2602.23940},
year = {2026}
}
Comments
5 pages, 2 figures. Accepted and presented at the Regional International Conference on Natural Language Processing (RegICON 2025), Gauhati University, Guwahati, India, November 27-29, 2025. To appear in the conference proceedings. Accepted papers list available at: https://www.regicon2025.in/accepted-papers