arXiv:2601.06306cs.CL2026-01被引 1

融合CNN与GRU注意力机制,提升孟加拉语仇恨言论检测性能

SyntaxMind at BLP-2025 Task 1: Leveraging Attention Fusion of CNN and GRU for Hate Speech Detection

  • 用BanglaBERT结合并行的CNN与GRU分支提取语义与局部特征
  • 在1A任务中获0.7345微F1(第2名),1B任务中达0.7317微F1(第5名)
  • 适合关注低资源语言文本分类与多模态特征融合的研究者

本文介绍我们在BLP-2025 Task 1:仇恨言论检测中的系统方案。我们参与了子任务1A和1B,针对孟加拉语文本中的仇恨言论分类问题。方法采用统一架构,融合BanglaBERT嵌入,并通过多个并行的GRU与CNN分支进行处理,随后经由注意力机制与全连接层完成最终分类。该模型旨在同时捕捉上下文语义与局部语言线索,实现跨子任务的稳健表现。所提系统展现出较强竞争力,在子任务1A中取得0.7345的微F1分数(第2名),在子任务1B中获得0.7317的微F1分数(第5名)。

原文摘要 · Abstract (English)

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.

仇恨言论检测孟加拉语序列建模多分支网络

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。