NLPineers@ NLU of Devanagari Script Languages 2025: Hate Speech Detection using Ensembling of BERT-based models

Nadika Poudel, Anmol Guragain, Rajesh Piryani, Bishesh Khanal


Abstract
This paper explores hate speech detection in Devanagari-scripted languages, focusing on Hindi and Nepali, for Subtask B of the CHIPSAL@COLING 2025 Shared Task. Using a range of transformer-based models such as XLM-RoBERTa, MURIL, and IndicBERT, we examine their effectiveness in navigating the nuanced boundary between hate speech and free expression. Our best performing model, implemented as ensemble of multilingual BERT models achieve Recall of 0.7762 (Rank 3/31 in terms of recall) and F1 score of 0.6914 (Rank 17/31). To address class imbalance, we used backtranslation for data augmentation, and cosine similarity to preserve label consistency after augmentation. This work emphasizes the need for hate speech detection in Devanagari-scripted languages and presents a foundation for further research. We plan to release the code upon acceptance.
Anthology ID:
2025.chipsal-1.37
Volume:
Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025)
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Kengatharaiyer Sarveswaran, Ashwini Vaidya, Bal Krishna Bal, Sana Shams, Surendrabikram Thapa
Venues:
CHiPSAL | WS
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
320–326
Language:
URL:
https://aclanthology.org/2025.chipsal-1.37/
DOI:
Bibkey:
Cite (ACL):
Nadika Poudel, Anmol Guragain, Rajesh Piryani, and Bishesh Khanal. 2025. NLPineers@ NLU of Devanagari Script Languages 2025: Hate Speech Detection using Ensembling of BERT-based models. In Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025), pages 320–326, Abu Dhabi, UAE. International Committee on Computational Linguistics.
Cite (Informal):
NLPineers@ NLU of Devanagari Script Languages 2025: Hate Speech Detection using Ensembling of BERT-based models (Poudel et al., CHiPSAL 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.chipsal-1.37.pdf