CEAF:囊网络增强了中国命名实体识别的功能融合架构
Siyu Ma1, Guangzhong Liu1, Yangshuyi Xu1
1College of Information Engineering, Shanghai Maritime University, Shanghai, China.
PloS one
|October 7, 2025
概括
通过使用新型深度学习技术,CEAF模型通过有效处理嵌套实体和边界模糊性来增强中文命名实体识别 (NER). 这种方法可以提高识别复杂实体结构的准确性.
科学领域:
- 自然语言处理自然语言处理.
- 人工智能的人工智能
- 深度学习 (Deep Learning) 是一种深度学习.
背景情况:
- 中国命名实体识别 (NER) 面临着嵌套实体和模糊边界的挑战.
- 现有的BiLSTM-CRF和变压器模型与层次结构和重叠跨度作斗争.
- 缺乏形态标记和几何建模阻碍了性能.
研究的目的:
- 提出一种新的神经架构,CEAF模型,用于改进中国NER.
- 解决模拟嵌套实体和解决边界模糊性的局限性.
- 为了利用几何深度学习来增强特征表示.
主要方法:
- 开发了CEAF模型,这是中国NER的多阶段神经架构.
- 使用BERT衍生子词嵌入和BiLSTM用于上下文和顺序模式.
- 引入了带有囊网络和位置感知注意力的深度上下文特征注意模块 (DCAM).
- 整合了自适应功能融合网络 (AFFN) 以实现功能集成.
主要成果:
- 与基线模型相比,CEAF模型在多个中文和英语NER数据集上表现出优异的性能.
- 实验证实了该模型在处理嵌套实体结构和边界模糊性方面的有效性.
- 可视化分析验证了模型的几何深度学习能力.
结论:
- CEAF模型为中国NER提供了显著的进步,特别是在复杂的实体识别方面.
- 囊网络和注意力机制的整合为层次和模两可的实体识别提供了强大的解决方案.
- 该研究强调了几何深度学习在推进NLP任务中的潜力.
相关概念视频
Tagging and Fusion Proteins
8.3K
Proteins are involved in several cellular processes and biochemical reactions. Analyzing a specific protein of interest requires it to be isolated from the other proteins in the cell. This is achieved by overexpressing the specific gene in a suitable host to produce large quantities of the target protein. A tag or label is recombined with the gene to produce a fusion protein containing the target protein and the tag. The tags on these fusion proteins can then be used for easy detection and...
8.3K
Fusion of Secretory Vesicles with the Plasma Membrane
16.5K
Proteins and neurotransmitters in secretory vesicles can be released from a cell upon vesicle docking, priming, and fusion with the plasma membrane. Vesicles are docked and primed in preparation for the quick exocytosis of their contents in response to a stimulus. The fusion process is mainly carried out by a SNAP Receptor or SNARE complex, consisting of synaptobrevin, syntaxin-1, and SNAP-25.
In 1993, Jim Rothman proposed that the antiparallel pairing of vesicular and transmembrane SNAREs, or...
In 1993, Jim Rothman proposed that the antiparallel pairing of vesicular and transmembrane SNAREs, or...
16.5K


