Corpus ID: 167213142

Chinese Named Entity Relation Extraction Based-on the Syntactic and Semantic Features

@inproceedings{Guo2014ChineseNE,
  title={Chinese Named Entity Relation Extraction Based-on the Syntactic and Semantic Features},
  author={Xiyue Guo and He Ting-ting and Hu Xiao-hua and Qianjun Chen},
  year={2014}
}
  • Xiyue Guo, He Ting-ting, +1 author Qianjun Chen
  • Published 2014
  • 基于句法语义特征的中文实体关系抽取 郭喜跃 ,何婷婷 ,胡小华 ,陈前军 1,4 (1.华中师范大学国家数字化学习工程技术研究中心,湖北省武汉市 430079; 2.华中师范大学计算机学院,湖北省武汉市 430079; 3.兴义民族师范学院信息技术学院,贵州省兴义市 562400; 4. 湖北大学信息与网络中心 湖北省武汉市 430062) 摘要:实体关系抽取的核心问题是实体关系特征的选择。以往的研究通常都以词法特征、实体原始特征等 来刻画实体关系,其抽取效果已难再提高。在传统方法的基础上,本文提出一种基于句法特征、语义特征 的实体关系抽取方法,融入了依存句法关系、核心谓词、语义角色标注等特征,选择 SVM 作为机器学习的 实现途径,以真实新闻文本作为语料进行实验。实验结果表明该方法的 F1 值有明显提升。 关键词:句法特征;语义特征;实体关系抽取;SVM 中图分类号:TP391 文献标识码:A 
    8 Citations
    Entity Relationship Extraction of Chinese Enterprises on Web Data
    • PDF
    Chinese Open Relation Extraction and Knowledge Base Establishment
    • 16
    Incorporating Forward and Backward Instances in a Bi-LSTM-CNN Model for Relation Classification
    • 1
    Research on Pattern Representation and Reliability in Semi-Supervised Entity Relation Extraction
    Semantic Technology
    • Siwei Yu
    • Computer Science
    • Lecture Notes in Computer Science
    • 2015
    • Highly Influenced
    A Novel Method for Open Relation Extraction from Public Announcements of Chinese Listed Companies
    • 3
    The Risk Assessment of Breast Tumors Based on Text Data of Ultrasound Reports

    References

    SHOWING 1-10 OF 11 REFERENCES
    Multi-instance Multi-label Learning for Relation Extraction
    • 587
    • PDF
    Kernel Methods for Relation Extraction
    • 770
    • PDF
    Sequential Minimal Optimization : A Fast Algorithm for Training Support Vector Machines
    • 2,623
    • Highly Influential
    • PDF
    Machine Learning in Action
    • 345
    Wrapper Induction for Information Extraction
    • 1,263
    • PDF
    LIBSVM: A library for support vector machines
    • 37,168
    • Highly Influential
    • PDF
    Predicting motor vehicle crashes using Support Vector Machine models.
    • 218
    • Highly Influential
    • PDF
    GongqingWu etc. A relation extraction method of Chinese named entities based on location and semantic features[J
    • Applied Intelligence,
    • 2013