计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (20): 113-116.

• 数据库、信号与信息处理 • 上一篇    下一篇

依存关系上的中文名词性谓词识别研究

王红玲1,2,袁晓虹1,2,王步康1,2,周国栋1,2   

  1. 1.苏州大学 计算机科学与技术学院,江苏 苏州 215006
    2.江苏省计算机信息处理技术重点实验室,江苏 苏州 215006
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-07-11 发布日期:2011-07-11

Nominal predicate identification for dependency-based Chinese semantic role labeling

WANG Hongling1,2,YUAN Xiaohong1,2,WANG Bukang1,2,ZHOU Guodong1,2

  

  1. 1.School of Computer Science and Technology,Soochow University,Suzhou,Jiangsu 215006,China
    2.Jiangsu Provincial Key Laboratory of Computer Information Processing Technology,Suzhou,Jiangsu 215006,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-07-11 Published:2011-07-11

摘要: 首次实现了一个基于依存关系的中文名词性谓词识别平台,作为语义角色标注的前提,谓词识别的结果直接影响语义角色标注的性能。使用两种方法进行实验:一种是基于传统的特征向量的方法在Chinese Nombank 的转换语料上进行了系统实验,对各种词法特征、结构特征及其组合进行了测试,标准语料上F1值达到89.65,自动语料上达到81.27。另一种是使用树核的方法进行探索性实验,在标准语料和自动语料上分别得到84.62和80.93的F1值。

关键词: 名词性谓词识别, 依存关系, 语义角色标注, 树核

Abstract: This paper implements a Chinese dependency-based nominal predicate identification system.Being the premise of Semantic Role Labeling(SRL),predicate identification plays a critical role.Two different ways are used in this paper.One is the traditional feather vector based predicate identification.In particular,various kinds of lexical and structure features are incorporated to improve the performance with systematic evaluation on the transferred corpus from Chinese Nombank.The system achieves 89.65 in labeled F1 for golden corpus,81.27 for automatic corpus.In another way,a tree kernel-based method is proposed to explore structural information.It achieves 84.62 in labeled F1 for golden corpus,80.93 for automatic corpus.

Key words: nominal predicate identification, dependency relationship, semantic role labeling, tree kernel