作　　者： ; ; ; ;

机构地区： 华南理工大学计算机科学与工程学院

出　　处： 《计算机科学》 2007年第7期208-210,共3页

摘　　要： 问句理解是问答系统的首要过程,问句分类是问句理解的主要组成部分,它在问答系统中具有非常重要的作用,因为问句类型有助于在文档中定位和抽取答案。问句分类的目标是基于预期的答案类型,准确地分类问句。本文提出依存关系规则与统计方法相结合,实现了基于依存关系的中文问句理解与问句分类机制。实验表明:支持向量机结合依存关系的特征抽取方法,获得了较高问句分类正确率。 Question interpretation is the first step of question answering system. Question classification is the main part of the question interpretation and it plays a crucial important role in the question answering system because categorizing a given question is beneficial to identify an answer in the documents. The goal of question classification is to accurately assign labels to question based on expected answer type. In this paper, we use dependency relation rules and statistical method to understand questions and classify questions. In this experiment, we perform the SVM algorithm and a dependency relationships feature extraction method to get high classification accuracy.

关 键 词： 问句分类 依存关系 依存关系树 命名实体识别

领　　域： [自动化与计算机技术] [自动化与计算机技术]