基于本体的受限领域问答系统研究  被引量:5

Chinese Restricted Domain Question Answering System Based on Ontology

在线阅读下载全文

作  者:刘杰[1,2] 樊孝忠[1] 王涛[1] 

机构地区:[1]北京理工大学计算机科学与技术学院,北京100081 [2]首都师范大学信息工程学院,北京100037

出  处:《广西师范大学学报(自然科学版)》2009年第1期169-172,共4页Journal of Guangxi Normal University:Natural Science Edition

基  金:国家自然科学基金资助项目(60773130);教育部高等学校博士学科点专项科研基金资助项目(20050007023)

摘  要:鉴于使用本体表示知识利于知识的重用及推理,提出基于本体知识库的受限领域问答系统(QA)框架,该框架可以方便地根据本体知识库和问句语义表征抽取答案。定义了本体的结构,以某医疗领域的本体为例分析本体元素之间的抽象关系;描述问句语义分析的方法,给出答案抽取的相关技术;分析问句类型,给出对应的问句语义表征和答案抽取策略。以某医疗领域的问答系统为实验平台,封闭测试F值为83.86%,开放测试F值为76.04%,效果良好。To express knowledge by ontology is favorable for reuse and reasoning of knowledge. A framework is put forward which can conveniently extract answer by question semantic representation based on ontology knowledge base. Ontology structure of restricted domain question answering system (QA) was defined, taking the ontology of certain hospital as example the abstract relation between ontology elements is analyzed;the method of analyzing semantically question is described ,the related technologies of answer extraction are presented;the question types are analyzed,and the corresponding question semantic representation and strategies for extracting answer are given out. Taking certain QA of medical domain as experimental platform,F-value reached 83.86% in the closed test,F-value reached 76.04% in the open test,which shows that the framework is practical.

关 键 词:问答系统 本体 问句语义分析 知识表示 

分 类 号:TP391[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象