Retriv at BLP-2025 Task 1: A Transformer Ensemble and Multi-Task Learning Approach for Bangla Hate Speech Identification
By: Sourav Saha, K M Nafi Asib, Mohammed Moshiul Hoque
Potential Business Impact:
Finds mean online messages in Bengali.
This paper addresses the problem of Bangla hate speech identification, a socially impactful yet linguistically challenging task. As part of the "Bangla Multi-task Hate Speech Identification" shared task at the BLP Workshop, IJCNLP-AACL 2025, our team "Retriv" participated in all three subtasks: (1A) hate type classification, (1B) target group identification, and (1C) joint detection of type, severity, and target. For subtasks 1A and 1B, we employed a soft-voting ensemble of transformer models (BanglaBERT, MuRIL, IndicBERTv2). For subtask 1C, we trained three multitask variants and aggregated their predictions through a weighted voting ensemble. Our systems achieved micro-f1 scores of 72.75% (1A) and 72.69% (1B), and a weighted micro-f1 score of 72.62% (1C). On the shared task leaderboard, these corresponded to 9th, 10th, and 7th positions, respectively. These results highlight the promise of transformer ensembles and weighted multitask frameworks for advancing Bangla hate speech detection in low-resource contexts. We made experimental scripts publicly available for the community.
Similar Papers
Bangla Hate Speech Classification with Fine-tuned Transformer Models
Computation and Language
Helps computers find hate speech in Bengali.
Gradient Masters at BLP-2025 Task 1: Advancing Low-Resource NLP for Bengali using Ensemble-Based Adversarial Training for Hate Speech Detection
Computation and Language
Finds hate speech in Bengali YouTube comments.
LLM-Based Multi-Task Bangla Hate Speech Detection: Type, Severity, and Target
Computation and Language
Helps stop online hate speech in Bangla.