计算机科学 ›› 2013, Vol. 40 ›› Issue (4): 185-192.

• 人工智能 • 上一篇    下一篇

事件前提和后果常识知识分析方法研究

李闪闪,曹存根   

  1. 首都师范大学计算机科学联合研究院北京100037;中国科学院计算技术研究所智能信息处理重点实验室北京100190
  • 出版日期:2018-11-16 发布日期:2018-11-16
  • 基金资助:
    本文受国家自然科学基金(30973713,3,61035004,4,91224006),国家社科基金(10AYY003)资助

Commonsense Knowledge Analysis Approach Based on Event Preconditions and Effects

LI Shan-shan and CAO Cun-gen   

  • Online:2018-11-16 Published:2018-11-16

摘要: 事件推理的研究需要事件的知识作支撑。事件知识作为一种常识性知识,其获取仍然是知识获取的瓶颈。提出一种事件知识分析方法,以从多个视角分析事件的前提和后果知识。在对事件知识分析中遵循基础分析、知识丰富、知识优化的流程。针对分析过程中所得知识不够全面和准确的问题,总结得出生理、心理、社会、物理世界4个常识知识角度,同时在知识丰富步骤中提出了角色细化的方法。实验表明,此方法能够得到较为全面和准确的事件知识。

关键词: 事件,常识知识角度,多视角常识分析,角色细化

Abstract: Event reasoning requires support of commonsense event knowledge.We proposed a method of event know-ledge analysis in order to analysize preconditions and effects of events from multiple perspectives.In the process of ana-lysis we followed three phases:fundamental analysis,knowledge supplement,and knowledge optimization.We summarized four common sense knowledge dimensions to solve the problem of comprehensiveness and accuracy in analysis,which are physiological,psychological,social and physical.The method of role specification was proposed in the know-ledge supplement phase.Experiments show that this method is promising for acquiring comprehensive and accurate commonsense event knowledge.

Key words: Event,Common sense knowledge dimension,Multi-perspective commonsense analysis,Role specification

[1] McCarthy J,Hayes P. Some philosophical problems from the standpoint of artificial intelligence[J]. Machine Intelligence,1969,4:463-502
[2] Shanahan M.The event calculus explained:Artificial Intelli-gence Today[C]∥Recent Trends and Developments.Berlin:Wooldrige M J,Veloso M M,1999:409-430
[3] Shanahan M.An abductive event calculus planner[J].The Journal of Logic Programming, 2000,4(1-3):207-240
[4] 朱景阳.基于贝叶斯方法的事件推理[J].科技信息,2010(33):219-225
[5] 董振东,董强.知网[EB/OL].http://www.keenage.com/
[6] Zhu Yao,Zang Liang-jun,Cao Ya-nan,et al.A Manual Experiment On Commonsense Knowledge Acquisition From Web Corpora[C]∥International Conference on Machine Learning and Cybernetics.Kunming,China,2008
[7] Cao Ya-nan,Cao Cun-gen,Cao Liang-jun,et al.Acquiring Commonsense Knowledge about Properties of Concepts from Text[C]∥5th International Conference on Fuzzy Systems and Knowledge Discovery.2008
[8] Cao Ya-nan,Cao Cun-gen,Cao Liang-jun,et al.Extracting Comparative Commonsense from the Web[C]∥6th International Conference on Intelligent Information Processing.2010
[9] 彭会良,曹存根.相关事件挖掘与角色联系发现的研究[J].计算机科学,2010,7(12):149-155
[10] 曹亚男.面向Web语料的因果知识获取研究[D].北京:中国科学院研究生院,2012
[11] Lenat D.CYC:A Large-scale Investment in knowledge Infrastructure[J].Communications of the ACM,1995,8(11):33-38
[12] Singh P.The Public Acquisition of Commonsense Knowledge[C]∥AAAI Spring Symposium on Acquiring Linguistic Know-ledge for Infoemation Acess.2002
[13] Chklovski T A.Using Analogy to Acquire Commonsense Know-ledge from Human Contributors[D]. Boston :Massachusetts Institute of Technology,2003
[14] 刘东立,姚天顺.自然语言处理中继承理论的分类和应用[J].东北大学学报,1997,8(5):486-489
[15] WordNet.A lexical database for the English language [EB/OL].http://wordnet.princeton.edu/
[16] Filatova E,Hatzivassiloglou V.Domain-independent detection,extraction,and labeling of actomic events[C]∥Proceeding of RANLP.2003:145-152
[17] 刘宗田,黄美丽,周文,等.面向事件的本体研究[J].计算机科学,2009,6(11):189-192
[18] 鲁川.知识工程语言学[M].北京:清华大学出版社,2010:245-248
[19] 鲁川,缑瑞隆,董丽萍.现代汉语基本句模[J].世界汉语教学,2000(4):11-24
[20] Nelson K,Gruendel J.Event Knowledge :Structure and Function in Develpoment[M].Hillsdale:Erlbaum,1986
[21] 周文.基于概念的若干知识表示模型及相关方法研究[D].上海:上海大学,2007
[22] 王寅.事件域认知模型及其解释力[J].现代汉语,2005,28(1):17-26
[23] Lenat D.The Dimensions of Context-Space[EB/OL].http://www.casbah.org/resources/cycContextSpace.shtml
[24] 彭会良.人物相关事件的常识知识获取方法研究[D].北京:首都师范大学,2010
[25] 阮智富,郭志新,乐嘉民,等.现代汉语大辞典[M].上海:汉语大词典出版社,2000:860-860

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!