基于疑问句句型识别的问题理解研究  

Research on Question Analysis Based on Sentence Type Recognition of Interrogative Sentences

作　　者：刘朝涛[1,2] 李祖枢[1,3] 

机构地区：[1]重庆大学智能自动化研究所,重庆400044 [2]重庆交通大学机电与汽车工程学院,重庆400074 [3]重庆工学院人工智能研究所,重庆400050

出　　处：《计算机科学》2008年第12期151-153,189,共4页Computer Science

摘　　要：问题理解是问答系统中的一个关键步骤。问题理解的过程包括疑问词分类、问句分词及词性标注、疑问句句型识别、问题分类及问题中心的识别等。提出了对疑问句句型的识别方法,即通过对疑问句的短语句法树的分析,得到疑问句的句型结构,通过计算句型结构与句型模式之间的相似度来识别句子的句型。结合疑问句的语法分析,通过识别疑问句的句型实现了问题理解。实验结果表明,该方法提高了问题理解的准确度。Question analysis is the primary task of question answering system. The process of the question analysis in this paper was described as follow： identifies the interrogative phrase class, parses words, identifies the question＇s sentence type, identifies the question class. A method of Sentence Type Recognition（STR） was put forward as.. the sentence type structure of a question results from analyzing the phase syntactic tree for the sentence, with computing the similarity between the sontence type structure and the sentence type modes, the question＇ s sentence type recognition is achieved. The result of experiments shows that the question analysis implemented by this way increases the precision of question classification.

关 键 词：问答系统 问题理解 句型识别 相似度 句法树 

分 类 号：TP391.3[自动化与计算机技术—计算机应用技术] TP391[自动化与计算机技术—计算机科学与技术]