多源文本知识融合算法分析
|
摘要
知识融合是知识管理和知识工程的重要环节,从文本中获取专业知识是人们获取新知识的首选方式。对于多源文本知识,由于作者描述的角度和侧重点不同,往往导致文本知识描述的整体性、知识粒度和精度有所差异,从而引起知识的不一致问题。为得到粒度小、精度高且完备的文本知识,提出一种基于本体的多源文本知识融合算法。利用本体概念框架将文本知识结构化,并将概念框架进行融合。实验结果表明,该算法有效解决了文本知识的不一致问题,提高了知识融合效率。
Knowledge fusion is an important part of knowledge management and knowledge engineering.Acquiring professional knowledge from text is the preferred way for people to acquire new knowledge.For multi-source text knowledge,different description angles and focuses of the authors,often lead to the differences in integrity of text knowledge description,knowledge granularity and precision and cause the problem inconsistent of knowledge.In order to obtain small-size,high precision and complete text knowledge,this paper proposes a multi-source text knowledge fusion algorithm based on ontology.Text knowledge are structured by ontology conceptual framework and integrated with it.Experimental results show that the presented knowledge fusion algorithm can effectively solve the problem of text knowledge inconsistency and improve the efficiency of knowledge fusion.
Knowledge fusion is an important part of knowledge management and knowledge engineering.Acquiring professional knowledge from text is the preferred way for people to acquire new knowledge.For multi-source text knowledge,different description angles and focuses of the authors,often lead to the differences in integrity of text knowledge description,knowledge granularity and precision and cause the problem inconsistent of knowledge.In order to obtain small-size,high precision and complete text knowledge,this paper proposes a multi-source text knowledge fusion algorithm based on ontology.Text knowledge are structured by ontology conceptual framework and integrated with it.Experimental results show that the presented knowledge fusion algorithm can effectively solve the problem of text knowledge inconsistency and improve the efficiency of knowledge fusion.
引文
[1]DENG Y,SHI W K.Experts′knowledge fusion in model-based diagnosis based on Bayes networks[J].Journal of Systems Engineering and Electronics,2003,14(2):25-30.
[2]徐赐军,李爱平,刘雪梅.基于本体的知识融合框架[J].计算机辅助设计与图形学学报,2010,22(7):1230-1236.
[3]周芳,王鹏波,韩立岩.多源知识融合处理算法[J].北京航空航天大学学报,2013,39(1):109-114.
[4]王爽,郭军海,张艳,等.导弹目标识别的最小贝叶斯风险分类器[J].现代防御技术,2012,40(1):60-64.
[5]DEMPSTER A P.Upper and lower probabilities induced by a multivalued mapping[J].Annals of Mathematical Statistics,1967,38(2):325-339.
[6]SHAFER G.A mathematical theory of evidence[M].Princeton,NJ:Princeton University Press,1976.
[7]李娜.基于本体的文本知识修正与获取[D].青岛:中国石油大学(华东),2009.
[8]韩永花,雷玉霞,陈娟,等.多框架知识的不一致性检测及其修正算法[J].计算机工程与应用,2016,52(23):94-97.
[9]张德海.NKI国家和地区地理知识的获取与分析[D].昆明:云南师范大学,2002.
[10]雷玉霞,陈娟,韩永花,等.Frame知识的不一致性分析与修正[J].计算机工程与应用,2016,52(22):155-158.
[11]百度百科[EB/OL].https:∥baike.baidu.com/item/%E5%A4%A7%E7%86%8A%E7%8C%AB/34935.
[12]维基百科[EB/OL].https:∥zh.wikipedia.org/wiki/%E5%A4%A7%E7%86%8A%E7%8C%AB.
[13]互动百科[EB/OL].http:∥www.baike.com/wiki/大熊猫&prd=so_1_doc.
[14]傅玉芳.汉语大词典[J].辞书研究,1994(3):80-81.
[15]《环境科学大词典》编委会.环境科学大辞典(修订版)[M].北京:中国环境科学出版社,2008.
[2]徐赐军,李爱平,刘雪梅.基于本体的知识融合框架[J].计算机辅助设计与图形学学报,2010,22(7):1230-1236.
[3]周芳,王鹏波,韩立岩.多源知识融合处理算法[J].北京航空航天大学学报,2013,39(1):109-114.
[4]王爽,郭军海,张艳,等.导弹目标识别的最小贝叶斯风险分类器[J].现代防御技术,2012,40(1):60-64.
[5]DEMPSTER A P.Upper and lower probabilities induced by a multivalued mapping[J].Annals of Mathematical Statistics,1967,38(2):325-339.
[6]SHAFER G.A mathematical theory of evidence[M].Princeton,NJ:Princeton University Press,1976.
[7]李娜.基于本体的文本知识修正与获取[D].青岛:中国石油大学(华东),2009.
[8]韩永花,雷玉霞,陈娟,等.多框架知识的不一致性检测及其修正算法[J].计算机工程与应用,2016,52(23):94-97.
[9]张德海.NKI国家和地区地理知识的获取与分析[D].昆明:云南师范大学,2002.
[10]雷玉霞,陈娟,韩永花,等.Frame知识的不一致性分析与修正[J].计算机工程与应用,2016,52(22):155-158.
[11]百度百科[EB/OL].https:∥baike.baidu.com/item/%E5%A4%A7%E7%86%8A%E7%8C%AB/34935.
[12]维基百科[EB/OL].https:∥zh.wikipedia.org/wiki/%E5%A4%A7%E7%86%8A%E7%8C%AB.
[13]互动百科[EB/OL].http:∥www.baike.com/wiki/大熊猫&prd=so_1_doc.
[14]傅玉芳.汉语大词典[J].辞书研究,1994(3):80-81.
[15]《环境科学大词典》编委会.环境科学大辞典(修订版)[M].北京:中国环境科学出版社,2008.