《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (10): 3111-3120.DOI: 10.11772/j.issn.1001-9081.2024101525

• 人工智能 • 上一篇    

结合边界信息的对比学习嵌套命名实体识别

范锦涛1,2,3, 陈艳平1,2,3, 杨采薇1,2,3, 林川1,2,3()   

  1. 1.文本计算与认知智能教育部工程研究中心(贵州大学),贵阳 550025
    2.公共大数据国家重点实验室(贵州大学),贵阳 550025
    3.贵州大学 计算机科学与技术学院,贵阳 550025
  • 收稿日期:2024-11-14 修回日期:2025-01-22 接受日期:2025-01-23 发布日期:2025-02-14 出版日期:2025-10-10
  • 通讯作者: 林川
  • 作者简介:范锦涛(2000—),男,贵州毕节人,硕士研究生,主要研究方向:信息抽取、自然语言处理
    陈艳平(1980—),男,贵州安顺人,教授,博士,CCF会员,主要研究方向:人工智能、自然语言处理
    杨采薇(1997—),女,贵州遵义人,博士研究生,CCF会员,主要研究方向:信息抽取、自然语言处理
    林川(1975—),男,贵州贵阳人,副教授,硕士,CCF会员,主要研究方向:大数据分析与处理、自然语言处理。
  • 基金资助:
    国家重点研发计划项目(2023YFC3304500);国家自然科学基金资助项目(62166007);黔科合重大专项([2024] 003号)

Nested named entity recognition by contrastive learning with boundary information

Jintao FAN1,2,3, Yanping CHEN1,2,3, Caiwei YANG1,2,3, Chuan LIN1,2,3()   

  1. 1.Text Computing and Cognitive Intelligence Engineering Research Center of National Education Ministry (Guizhou University),Guiyang Guizhou 550025,China
    2.State Key Laboratory of Public Big Data (Guizhou University),Guiyang Guizhou 550025,China
    3.College of Computer Science and Technology,Guizhou University,Guiyang Guizhou 550025,China
  • Received:2024-11-14 Revised:2025-01-22 Accepted:2025-01-23 Online:2025-02-14 Published:2025-10-10
  • Contact: Chuan LIN
  • About author:FAN Jintao, born in 2000, M. S. candidate. His research interests include information extraction, natural language processing.
    CHEN Yanping, born in 1980, Ph. D., professor. His research interests include artificial intelligence, natural language processing.
    YANG Caiwei, born in 1997, Ph. D. candidate. Her research interests include information extraction, natural language processing.
    LIN Chuan, born in 1975, M. S., associate professor. His research interests include big data analysis and processing, natural language processing.
  • Supported by:
    National Key Research and Development Program of China(2023YFC3304500);National Natural Science Foundation of China(62166007);Key Technology Research and Development Program of Guizhou Province([2024]003)

摘要:

现有对比学习(CL)方法在嵌套命名实体识别(NER)任务中存在以下2个主要缺点:1)枚举生成的候选实体作为对比学习的对象,缺失上下文语义依赖和边界信息;2)产生不必要的噪声和无效信息,增加模型的计算负担且弱化了对比学习的性能,提出一个两阶段命名实体识别框架。在第一阶段,通过边界识别模型生成候选实体边界,并通过边界集成模块生成候选实体,减少不必要的负候选实体的生成;同时,在候选实体两侧插入注意力线索,生成对应的候选实体文本,使得模型能够感知上下文语义和边界信息。在第二阶段,提出一个双编码框架用于识别实体,通过对比学习将候选实体文本和实体类型注释映射到相同向量表征空间中,对比的对象不再是候选实体,而是带有注意力线索的句子。此外,设计带有标签语义的分类参数矩阵,丰富模型对候选实体的理解能力。实验结果表明,与Binder方法相比,所提方法在GENIA、ACE2005和ACE2004这3个嵌套数据集上的F1值分别提升了1.22、3.42和2.31个百分点,验证了所提方法对嵌套NER任务的有效性。

关键词: 对比学习, 边界信息, 双编码器, 标签语义, 嵌套命名实体识别

Abstract:

To address the following two major drawbacks of existing Contrastive Learning (CL) methods for the nested Named Entity Recognition (NER) tasks: 1) candidate entities by greedily enumerating in contrastive learning lack contextual semantics and boundary information, 2) unnecessary noise and invalid information increases computational burden and weakens contrastive learning performance, a two-stage NER framework was proposed. In the first stage, candidate entity boundaries were generated by the boundary recognition model, and candidate entities were integrated by the boundary integration module to minimize unnecessary negative candidates. Attention cues were inserted on both sides of the candidate entities to generate corresponding candidate entity texts, allowing the model to perceive contextual semantics and boundary information. In the second stage, a bi-encoder framework mapped candidate entity texts and entity label annotations into the same vector representation space through contrastive learning, with the comparison objects being sentences with attention cues rather than candidate entities. In addition, a classification parameter matrix with label semantics was designed to enrich the model’s understanding of candidate entities.Experimental results show that compared with Binder method, the proposed method improves the F1 values of 1.22, 3.42 and 2.31 percentage points, respectively, on three nested datasets: GENIA, ACE2005 and ACE2004, which verifies the effectiveness of the proposed method for tasks of nested NER.

Key words: Contrastive Learning (CL), boundary information, bi-encoder, label semantics, nested Named Entity Recognition (NER)

中图分类号: