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 ›› 2012, Vol. 38 ›› Issue (7): 131-133. doi: 10.3969/j.issn.1000-3428.2012.07.043

• 人工智能及识别技术 • 上一篇    下一篇

篇章连贯语义关系的自动标注方法

姚双云a,胡金柱a,舒江波b,沈 威a   

  1. (华中师范大学 a. 语言与语言教育研究中心;b. 国家数字化学习工程技术研究中心,武汉 430079)
  • 收稿日期:2011-06-20 出版日期:2012-04-05 发布日期:2012-04-05
  • 作者简介:姚双云(1972-),男,副教授、博士,主研方向:中文信息处理;胡金柱,教授、博士生导师;舒江波、沈 威,讲师、博士
  • 基金资助:
    国家自然科学基金资助项目(60773167);教育部人文社科重点研究基金资助重大项目(10JJD740012)

Automatic Annotation Method of Textual Coherence Semantic Relationship

YAO Shuang-yun a, HU Jin-zhu a, SHU Jiang-bo b, SHEN Wei a   

  1. (a. Center for Language and Language Education; b. National Engineering Research Center for E-Learning, Huazhong Normal University, Wuhan 430079, China)
  • Received:2011-06-20 Online:2012-04-05 Published:2012-04-05

摘要: 为实现篇章连贯语义关系的判定与自动标注,提出一种综合运用关联词多种语法信息的自动标注方法。该方法利用关联词的词性分布规则排除非关联词,标注出潜在关联词,对比关联词库中的模式表,并综合利用搭配距离、搭配强度和句法位置获取合法的篇章连贯模式,在此基础上标注出其语义关系。通过实验验证了该方法的有效性。

关键词: 篇章连贯, 语义关系, 搭配距离, 搭配强度, 句法规则, 自动标注

Abstract: This paper provides a method of the automatic annotation by means of the synthetic use of the grammatical information to realize the judgment and automatic annotation of the semantic relationship of textual coherence. The distribution rules of the parts of speech are used to eliminate the non-conjunctions, and the potential conjunctions are tagged. The pattern of the textual coherence is obtained by the synthetic use of the collocation distance, collocation strength and syntactic position after matching the pattern in the corpus of conjunctions. Based on the above data, the semantic relationship is tagged. Experiment shows that the method is effective.

Key words: textual coherence, semantic relationship, collocation distance, collocation strength, syntactic rule, automatic annotation

中图分类号: