Scholarlink

<p>Chinese Named Entity Recognition (CNER) is a fundamental and crucial task in information extraction. In recent years, pre-trained language and lexicon-based models have proven more powerful than the previous character-based models in CNER tasks. However, existing lexicon-enhanced BERT models neither integrate lexical knowledge into the fundamental layers of the bidirectional transformer model nor explicitly align character features with lexicon features. In this paper, we propose a spatial-aware lexicon adapter (SALA), a neural adapter capable of dynamically integrating character and lexical representations through spatial-aware attention. SALA is incorporated between the layers of BERT to inject lexical information into the deep contextual representations of corresponding character sequences. The resulting fused vectors are further trained in SALA-BERT to enhance CNER. We evaluate SALA-BERT on various Chinese NER tasks. Compared to previous state-of-the-art models, it achieves comparable or better performance.</p>

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

Lexicon-enhanced transformer with spatial-aware integration for Chinese named entity recognition

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月3日

查看全文
  • Jiachen Huang,
  • Shuo Liu

摘要

Chinese Named Entity Recognition (CNER) is a fundamental and crucial task in information extraction. In recent years, pre-trained language and lexicon-based models have proven more powerful than the previous character-based models in CNER tasks. However, existing lexicon-enhanced BERT models neither integrate lexical knowledge into the fundamental layers of the bidirectional transformer model nor explicitly align character features with lexicon features. In this paper, we propose a spatial-aware lexicon adapter (SALA), a neural adapter capable of dynamically integrating character and lexical representations through spatial-aware attention. SALA is incorporated between the layers of BERT to inject lexical information into the deep contextual representations of corresponding character sequences. The resulting fused vectors are further trained in SALA-BERT to enhance CNER. We evaluate SALA-BERT on various Chinese NER tasks. Compared to previous state-of-the-art models, it achieves comparable or better performance.