SyntaxMind at BLP-2025 Task 1: Leveraging Attention Fusion of CNN and GRU for Hate Speech Detection
This work addresses hate speech classification for Bangla language users, presenting an incremental improvement in a domain-specific task.
The paper tackled hate speech detection in Bangla text by developing a unified architecture that integrates BanglaBERT embeddings with GRU and CNN branches, achieving competitive results with micro F1-scores of 0.7345 (2nd place) in Subtask 1A and 0.7317 (5th place) in Subtask 1B.
This paper describes our system used in the BLP-2025 Task 1: Hate Speech Detection. We participated in Subtask 1A and Subtask 1B, addressing hate speech classification in Bangla text. Our approach employs a unified architecture that integrates BanglaBERT embeddings with multiple parallel processing branches based on GRUs and CNNs, followed by attention and dense layers for final classification. The model is designed to capture both contextual semantics and local linguistic cues, enabling robust performance across subtasks. The proposed system demonstrated high competitiveness, obtaining 0.7345 micro F1-Score (2nd place) in Subtask 1A and 0.7317 micro F1-Score (5th place) in Subtask 1B.