作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程

• 人工智能及识别技术 • 上一篇    下一篇

基于CCRF的领域本体概念上下位关系抽取

莫媛媛a,郭剑毅a,b,余正涛a,b,蒋年树a,线岩团a,b   

  1. (昆明理工大学 a. 信息工程与自动化学院;b. 智能信息处理重点实验室,昆明 650051)
  • 收稿日期:2013-05-23 出版日期:2014-06-15 发布日期:2014-06-13
  • 作者简介:莫媛媛(1989-),女,硕士研究生,主研方向:自然语言处理,信息抽取;郭剑毅(通讯作者)、余正涛,教授;蒋年树,硕士研究生;线岩团,讲师。
  • 基金资助:
    国家自然科学基金资助项目(61175068);云南省应用基础研究计划基金资助重点项目(2013FA030);云南省教育厅重大专项基金资助项目(KKJI201203001)。

Hyponymy Extraction of Domain Ontology Concept Based on CCRF

MO Yuan-yuan a, GUO Jian-yi a,b, YU Zheng-tao a,b, JIANG Nian-shu a, XIAN Yan-tuan a,b   

  1. (a. School of Information Engineering and Automation; b. Key Laboratory of Intelligent Information Processing, Kunming University of Science and Technology, Kunming 650051, China)
  • Received:2013-05-23 Online:2014-06-15 Published:2014-06-13

摘要: 现有领域本体概念上下位关系抽取方法受到手工标注和特定模式的限制。针对该问题,提出一种基于层叠条件随机场的领域本体概念上下位关系抽取方法。以自由文本为抽取对象,采用两层条件随机场算法,将训练数据处理成条件随机场能识别的线性结构。低层条件随机场模型考虑词之间的长距离依赖,对词进行建模,识别出领域概念并对概念进行顺序组合,结合模板定义特征得到概念对;高层模型对成对概念进行上下位语义标注,识别出领域本体概念之间的上下位关系。采用真实语料进行实验,结果表明,该方法具有较好的识别效果。

关键词: 层叠条件随机场, 领域本体概念, 上下位关系, 概念对, 关系抽取

Abstract: Existed hyponymy extraction methods of domain ontology concept are limited by manual annotation and specific patterns. Aiming at this problem, this paper proposes a hyponymy extraction method of domain ontology concept based on Cascaded Conditional Random Field(CCRF). It uses free text as extracting object, adopts two layers conditional random fields identifying the domain concepts. In lower-level conditional random fields model, it considers long distance dependence between words, makes modeling for words, and extracts concept in sequential, then obtains the concept with the characteristics of the template definition; In high-level model, it annotates semantic in pairs of concepts with hyponymy, identifies the hyponymy relation between domain ontology concept. Through real corpus open testing, the experimental results demonstrate the proposed method performs better.

Key words: Cascaded Conditional Random Field(CCRF), domain ontology concept, hyponymy, concept pair, relation extraction

中图分类号: