基于句法语义特征的中文实体关系抽取

Chinese Named Entity Relation Extraction Based on Syntactic and Semantic Features

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,该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。

Identifying the relation features between named entities is the key aspect in named entity relation extrac- tion. Traditional methods usually chose the lexical features and other surface features, which are well addressed al- ready. This paper proposes a novel Chinese named entity relation extraction method, adding such syntactic and se- mantic features as dependency parsing, core predicate verb and semantic role labeling etc. Experimented by SVM o- ver a true news text corpus, the results indicate that this method could improve the F1 value significantly.