Scholarlink

Text classification assigns text to predefined categories. Traditional methods struggle with complex structures and long-range dependencies. Deep learning with recurrent neural networks and Transformer models has improved feature extraction and context awareness. However, these models still trade off interpretability, efficiency and contextual range. We propose the Dynamic Bid-irectional Elman Attention Network (DBEAN). DBEAN combines bidirectional temporal modeling and self-attention. It dynamically weights critical input segments and preserves computational efficiency. Code is available at https://github.com/doomx1/DBEAN .

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Dual-Directional Context-Aware Test-Time Learning for Text Classification

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Dong Xu,
  • Mengyao Liao,
  • Zhenglin Lai,
  • Xueliang Li,
  • Junkai Ji

摘要

Text classification assigns text to predefined categories. Traditional methods struggle with complex structures and long-range dependencies. Deep learning with recurrent neural networks and Transformer models has improved feature extraction and context awareness. However, these models still trade off interpretability, efficiency and contextual range. We propose the Dynamic Bid-irectional Elman Attention Network (DBEAN). DBEAN combines bidirectional temporal modeling and self-attention. It dynamically weights critical input segments and preserves computational efficiency. Code is available at https://github.com/doomx1/DBEAN .