Scholarlink

<p>Named Entity Recognition (NER), prevalent in real-world applications, has evolved from flat to complex nested and discontinuous structures. However, existing sequence labeling and span-based methods struggle to unify these varied types efficiently and to effectively integrate complementary semantic context and boundary cues. To address these limitations, we propose UHIF, a <b>U</b>nified framework via <b>H</b>eterogeneous <b>I</b>nformation <b>F</b>usion for flat, nested, and discontinuous NER. It leverages a token-pair feature matrix by systematically distinguishing its upper-triangular region for ‘NEXT’ (token-to-immediate-next) labels and its lower-triangular region for ‘SPAN-*’ (head-tail) labels. This representation allows a path-search decoding algorithm to naturally identify flat, nested, and gapped entities simultaneously. To construct this matrix, we employ two specialized modules to capture contextualized semantic information and explicit boundary information, respectively, and leverage the designed Heterogeneous Channel Attention Module (HCAM) to intelligently refine the mixed features—achieving a dynamic balance between semantic and boundary information by modeling cross-channel interactions. Extensive experiments on four diverse datasets (GENIA, CADEC, CoNLL2003, and Resume) demonstrate that UHIF achieves superior performance, obtaining F1 scores of 81.80%, 74.86%, 93.45%, and 96.86%, respectively.</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

UHIF: a unified framework via heterogeneous information fusion for flat, nested, and discontinuous NER

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月26日

查看全文
  • Jikun Dong,
  • Fangfang Li,
  • Bin Ge

摘要

Named Entity Recognition (NER), prevalent in real-world applications, has evolved from flat to complex nested and discontinuous structures. However, existing sequence labeling and span-based methods struggle to unify these varied types efficiently and to effectively integrate complementary semantic context and boundary cues. To address these limitations, we propose UHIF, a Unified framework via Heterogeneous Information Fusion for flat, nested, and discontinuous NER. It leverages a token-pair feature matrix by systematically distinguishing its upper-triangular region for ‘NEXT’ (token-to-immediate-next) labels and its lower-triangular region for ‘SPAN-*’ (head-tail) labels. This representation allows a path-search decoding algorithm to naturally identify flat, nested, and gapped entities simultaneously. To construct this matrix, we employ two specialized modules to capture contextualized semantic information and explicit boundary information, respectively, and leverage the designed Heterogeneous Channel Attention Module (HCAM) to intelligently refine the mixed features—achieving a dynamic balance between semantic and boundary information by modeling cross-channel interactions. Extensive experiments on four diverse datasets (GENIA, CADEC, CoNLL2003, and Resume) demonstrate that UHIF achieves superior performance, obtaining F1 scores of 81.80%, 74.86%, 93.45%, and 96.86%, respectively.