汉语句群领域的自动抽取研究  

Research on extracting conceptual domain of sentence group in Chinese

作　　者：韦向峰[1] 缪建明[1] 张全[1] 

机构地区：[1]中国科学院声学研究所,北京100190

出　　处：《计算机工程与应用》2009年第4期11-15,共5页Computer Engineering and Applications

基　　金：国家重点基础研究发展规划(973)No.2004CB318104;国家科技支撑计划课题No.2007BAH05B02-05;中科院声学所知识创新工程项目No.O654091431;中国科学院声学研究所"所长择优基金"No.GS13SJJ04;中国科学院青年人才领域前沿项目No.O754021432~~

摘　　要：句群是介于句子和段落之间的一个处理单位。在语言概念空间句群有三个要素:领域、情景和背景,领域是最根本的。获取了句群领域,就能够确定情景框架,这对信息抽取和文本分类都是非常重要的。一些词语的概念符号中蕴含了领域信息,通过分析词语在句子中的语义角色以及词语位置、频次等可以得到句子的领域。根据领域关系可以合并领域相同或相似的句子,得到句群及其领域。实验表明,常见的四种领域关系能够很好地被处理,但在动态词处理、复合领域的识别等方面还需要改进。Sentence group is a processing unit between sentence and paragraph.It is composed of three elements：domain,situation and background,but domain is the most essential.Once the domain of sentence group is obtained,the situation will be exposed.This is very important for information retrieval and text classification.The symbols of domain are contained in some words.The domain of a sentence can be analyzed by the semantic role,position and frequency of words.Sentence group and its domain can be extracted by combining sentences with the same or similar domain.The experiment shows that the four kinds of relationships between two domains are processed well.However,the process of dynamic words and the recognition of complex domain should be improved.

关 键 词：句群 领域 概念层次网络理论 信息抽取 文本分类 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]