基于语料库和规则库的石油本体自动构建研究

详细信息    查看全文 | 推荐本文 |

英文篇名：Research on Automatic Construction of Petroleum Domain Ontology Based on Corpus and Rule Base 作者：文必龙 ; 段炼 ; 汪志群 ; 李云静 ; 王琪超 英文作者：WEN Bi-long;DUAN Lian;WANG Zhi-qun;LI Yun-jing;WANG Qi-chao;School of Computer and Information Technology,Northeast Petroleum University; 关键词：语料库 ; 规则库 ; 领域本体 ; 本体自动构建 英文关键词：corpus;;rule base;;domain ontology;;ontology automatic construction 中文刊名：WJFZ 英文刊名：Computer Technology and Development 机构：东北石油大学计算机与信息技术学院; 出版日期：2015-08-26 15:35 出版单位：计算机技术与发展 年：2015 期：v.25;No.221 基金：国家科技重大专项(2011ZX05023-005-012) 语种：中文; 页：WJFZ201509046 页数：4 CN：09 ISSN：61-1450/TP 分类号：215-218

摘要

石油领域文本所蕴含的信息丰富但其数目繁多复杂,现有大多数本体都是通过手工构建的,这种方法难以方便快捷地抽取文本信息,难以构建一个较完善的石油领域本体。为提高本体构建的效率,文中综述了本体的主要概念,分析了本体构建的一般原则和方法。利用文本处理软件对文本进行分词处理,生成特征词集并对其进行缩减,利用Petro-Onto方法实现语料库的构建,提出了基于语料库和规则库区分概念、属性并抽取它们之间关系的方法。该方法能大大提高本体的构建效率,并在一定程度上保证结果本体的质量,达到了本体自动建立的目的。
        Texts of petroleum domain contain rich but numerous and complex information,and most existing ontology are built by manual. But this method is difficult to extract information in text conveniently and rapidly and build a complete text of petroleum domain. In order to improve the efficiency of building ontology,sum up the main concept of ontology and analyze the general principles and methods. Use text processing software to segment words and generate feature word set,then shrinking them. Through building corpus through Petro-Onto,propose a method based on distinguishing concepts and attributes of corpus and rule base and extract the relationships between them. This method can greatly improve the efficiency of building ontology and can guarantee the quality of the result of ontology,and eventually achieve the purpose of building text automatically.

引文

[1]文必龙,张莉.石油勘探开发领域本体的构建方法研究[J].计算机工程与应用,2009,45(34):1-3.
    [2]杜睿山,尚福华,吴雅娟.基于本体的石油开发领域知识构建研究[J].科学技术与工程,2010,10(19):4656-4662.
    [3]朱恒民,姬小利,黄卫东,等.电信领域本体构建方法研究[J].现代情报,2008,28(1):184-186.
    [4]王进.基于本体的语义信息检索研究[D].合肥:中国科学技术大学,2006.
    [5]Zhong J,Aydina A,Mc Guinness D L.Ontology of fractures[J].Journal of Structural Geology,2009,31(3):251-259.
    [6]Raskin R.Guide to SWEET ontologies[R].Pasadena:NASA/Jet Propulsion Lab,2013.
    [7]徐力斌,刘宗田,周文,等.基于Word Net和自然语言处理技术的半自动领域本体构建[J].计算机科学,2007,34(6):219-222.
    [8]López M F,Gómez-Pérez A,Sierra J P,et al.Building a chemical ontology using methontology and the ontology design environment[J].IEEE Intelligent Systems&Their Applications,1999,14(1):37-46.
    [9]Uschold M,King M.Towards a methodology for building ontology[C]//Proc of international joint conference on artificial intelligence.[s.l.]:[s.n.],1995:373-380.
    [10]王晓盈,王晓璇,刘鹏.中文本体构建及可视化研究[J].计算机技术与发展,2010,20(2):121-124.
    [11]陈晓云.文本挖掘若干关键技术研究[D].上海:复旦大学,2005.
    [12]徐健,张智雄,吴振新.实体关系抽取的技术方法综述[J].现代图书情报技术,2008(8):18-23.
    [13]刘威.基于中文文本的本体构建方法研究[D].哈尔滨:哈尔滨工程大学,2008.
    [14]杜小勇,李曼,王珊.本体学习研究综述[J].软件学报,2006,17(9):1837-1847.
    [15]鲍文,李冠宇.本体存储技术研究[J].计算机技术与发展,2008,18(1):146-150.