浅层语义分析及SPARQL在问答系统中的应用  

Application of shallow semantic analysis and SPARQL in question answering system

作　　者：张巍[1] 陈俊杰[2] 

机构地区：[1]太原理工大学计算机与软件学院,太原030024 [2]山西职工医学院信息中心,太原030012

出　　处：《计算机工程与应用》2011年第2期118-120,共3页Computer Engineering and Applications

基　　金：国家自然科学基金(No.60970059);山西省国际科技合作计划项目(No.2009081022)~~

摘　　要：为了解决受限域问答系统中答案抽取的问题,提出了一种基于浅层语义分析的问答系统模型。该模型以自然语言为接口,利用医院信息本体,采用浅层语义分析技术,由语义块定义规则和语义块判定规则,首先生成问句向量,然后利用SPARQL查询技术,在本体中进行查询,从而得到答案。实验表明该方法可行,对自动问答系统的设计具有借鉴意义和深入研究的价值。To solve the problem of the answer extraction of restricted-domain question answering system,a question answering system model based on shallow semantic parsing is presented.A natural language interface is provided,the ontology of the hospital information is utilized and shallow semantic parsing technology is applied in the model.According to the rules of the definition and determination of semantic chunk,the question vector is firstly generated,then SPARQL query technology is utilized,the answer is obtained by querying in the ontology.The experiments proves that it is feasible to use the method to develop a question answering system,it is valuable for further study in more depth.

关 键 词：问答系统 浅层语义分析 自然语言处理 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]