期刊文献+

AnswerSeeker:基于互联网挖掘的智能问答系统 被引量:4

AnswerSeeker:Question Answering System Based on Web Mining
下载PDF
导出
摘要 智能问答系统是一种处理自然语言的新型的信息检索系统。介绍了AnswerSeeker智能问答系统,该系统采用了模块化和可扩展的框架,以便整合多种智能问答技术和多样化数据源。通过将与语言无关的代码和语言相关的代码分离,并且将语言相关的代码封装为组件,只要替换相应的组件,该系统可以适用于多种语言。由于很多自然语言处理技术还没有针对中文的,目前为止,我们系统的内核只支持英文,所以将以英语自然语言为例介绍AnswerSeeker的架构和工作原理。该系统采用了两种互联网挖掘的方法来寻找问题的答案:知识挖掘和知识诠释。AnswerSeeker使用网络作为一个知识源,当然它也可以使用其他小的语料库或面向专业领域的知识库作为知识源。此外,提出了一种新的问题的表示和答案提取的方法一文本模式,文本模式分为问题模式和答案模式;其中问题模式用来表示问题,答案模式用来提取精确的答案。AnswerSeeker通过将问题-答案对作为训练数据,自动学习答案模式。实验表明将互联网作为知识源,将模式学习和知识诠释的技术集成在同一系统中进行答案挖掘是一种这种很有前途的方法。 This paper describes the AnswerSeeker question answering engine,a modular and extensible framework that allows integrating multiple approaches to question answering in one system.It supports the two major approaches to question answering,knowledge annotation and knowledge mining.In addition,it proposes one novel approach to question interpretation which abstracts from the original formulation of the question. Text patterns are used to interpret a question and to extract answers from text snippets.Our system automatically learns the patterns for answer extraction,using question-answer pairs as training data. Experimental results reveal the potential of AnswerSeeker.
出处 《计算机系统应用》 2010年第1期6-17,共12页 Computer Systems & Applications
基金 北京市大学生科学研究和创业行动计划(0832)
关键词 互联网挖掘 知识挖掘 知识诠释 模式学习 智能问答 Web mining knowledge mining knowledge annotation pattern learning question answering
  • 相关文献

参考文献9

  • 1Prager J.Open-Domain Question Answering. America: World Scientific, Jan. 2007.
  • 2Nyberg E, Frederking R, Mitamura T, Bilotti M, Hannan K, Hiyakumoto L, Ko J, Lin F, Lita L, Pedro V, Schlaikjer A. JAVELIN I and II systems at TREC 2005. Proc. of the 14th Text REtrieval Conference. 2005.
  • 3Metamora M, Lin F, Shima H, Wang M, Ko J, Betteridge J, Bilotti M, Schlaikjer A, Nyberg E. JAVELIN III: Cross-lingual question answering from Japanese and Chinese documents. Proc. of the NTCIR- 6. 2007.
  • 4Katz B, Felshin S, Yuret D, Ibrahim A, Lin J, Matron G Jerome A, Temelkuran B. Omnibase: Uniform access to heterogeneous data for question answering. Proc. of the 7th International Workshop on Applications of Natural Language to Information Systems (NLDB 2002). 2002.
  • 5Katz B, Lin J, Felshin S. The START multi-media information system: Current technology and future directions. Proc. of the International Workshop on Multimedia Information Systems (MIS 2002). 2002.
  • 6Katz B. Annotating the World Wide Web using natural language. Proc. of the 5th RIAO Conference on Computer Assisted Information Searching on the Intemet (RIAO'97). 1997.
  • 7Zhang D, Lee W. Web-Based pattern mining and matching approach to question answering. Proc. of the 11 th Text Retrieval Conference. 2002.
  • 8Ellen M. Overview of the TREC-9 Question Answering Track. Proc. of the Ninth Text Retrieval Conference. 2001.71 - 80.
  • 9Ellen M. Overview of the TREC 2002 question answering track. Proc. of the 11th Text Retrieval Conference. 2002.

同被引文献38

引证文献4

二级引证文献3

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部