| 摘要: |
| 命名实体识别任务是信息抽取领域中的一个基础任务, 旨在定位句子中实体所在位置的边界, 并对该实体进行分类. 针对现有基于跨度检测的模型存在的嵌套实体边界模糊问题, 提出一种基于跨度边界感知的嵌套命名实体识别模型. 首先, 利用双仿射注意力机制, 捕获词元间的语义相关性, 进而生成跨度语义表示矩阵; 其次, 通过设计一种二阶对角邻域差分算子, 建立跨度语义差分机制, 以提取跨度间的语义差异信息. 此外, 引入一种跨度边界感知机制, 利用滑动窗口的局部特征提取能力, 强化跨度的边界语义差异, 从而准确定位实体跨度位置. 为验证模型的有效性, 在3个基准数据集上进行测试, 包括ACE04、ACE05和Genia数据集. 实验结果表明, 提出的模型在实体识别准确率的表现优于相关工作. 此外, 还设计消融实验和案例分析以验证提出的语义差分机制和跨度边界感知机制的有效性, 为进一步研究命名实体识别问题提供新的思路和实验证据. |
| 关键词: 嵌套命名实体识别 跨度分类 差分算子 双仿射注意力机制 跨度语义感知 |
| DOI：10.13328/j.cnki.jos.007040 |
| 分类号:TP391 |
| 基金项目:国家自然科学基金(U19B2028, U22B2061); 国家重点研发计划(2022YFB4300603); 四川省科技计划(2023YFG0151) |
|
| Nested Named Entity Recognition Based on Span Boundary Perception |
|
CAI Yu-Xiang1, LUO Da1, GAN Yang-Lei1, HOU Rui1, LIU Xue-Yi1, LIU Qiao1, SHI Xiao-Jun2
|
|
1.School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China;2.Institute of Information Science, China Electronics Technology Group Corporation, Beijing 100086, China
|
| Abstract: |
| Named entity recognition (NER) is a fundamental task in information extraction and aims to locate the boundaries of entities in a sentence and classify them. In response to the fuzzy boundaries of nested entities based on span detection models, this study proposes a nested NER model based on span boundary perception. Firstly, it utilizes a bidirectional affine attention mechanism to capture the semantic relevance among word tokens and then generates a span semantic representation matrix. Secondly, it designs a second-order diagonal neighborhood difference operator and establishes a span semantic difference mechanism to extract semantic difference information among spans. Additionally, a span boundary perception mechanism is introduced to employ the local feature extraction ability of sliding windows to enhance the span boundary semantic differences, thereby accurately locating the entity span. The model is validated on three benchmark datasets of ACE04, ACE05, and Genia. The experimental results show that the proposed model outperforms related work in entity recognition accuracy. Additionally, the study conducts ablation experiments and case studies to verify the effectiveness of the proposed semantic difference mechanism and span boundary perception mechanism, providing new ideas and empirical evidence for further research on NER. |
| Key words: nested named entity recognition span classification difference operator bidirectional affine attention mechanism span semantic cognition |
