期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

开放领域的QA系统结构及性能分析

Structure and Performance Analysis of Open Domain QA System
原文传递
导出
摘要 开放领域的问题回答(QA)是近年来自然语言处理研究领域的一个热门研究方向.文中介绍基于模式匹配策略的问题回答系统,并对其进行深层次的性能分析与评价,讨论检索参数和训练样例数目对系统性能的影响.同时,进行t-test来检验不同因素对系统性能影响的显著性,旨在对系统实现细节有更明确的分析,更有效地提高系统性能.系统中运用自然语言处理工具,如句法分析器、实体名识别工具等,工具本身的性能也是影响QA系统性能的一个重要因素. Open domain question answering （QA） has drawn much attention from the natural language processing communities. A pattern based question answering system is introduced, and the deep performance analysis and the evaluation of the QA system are presented. The impact of parameter tuning and training set size on system performance is discussed as well. Meanwhile, the t-test results denote the significance of the performance improvement by different factors. Natural language processing tools are used in the QA system, such as the syntax parser and the named entity recognition tool. Analysis results indicate that these tools play an important role in the QA system.
作者 杜永萍 黄萱菁
机构地区 北京工业大学计算机学院 复旦大学计算机科学与工程系
出处 《模式识别与人工智能》 EI CSCD 北大核心 2009年第4期527-531,共5页 Pattern Recognition and Artificial Intelligence
基金 国家自然科学基金重点项目(No.60435020) 国家自然科学基金青年基金项目(No.60803086)资助
关键词 问题回答 性能分析 自然语言处理 Question Answering, Performance Analysis, Natural Language Processing
分类号 TP391.1 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献8

  • 1Moldvan D I, Rus V. Logic Form Transformation of WordNet and Its Applicability to Question Answering // Proc of the 39th Annual Meeting of the Association for Computational Linguistics. Toulouse, France, 2001:402-409.
  • 2Soubbotin M M, Soubbotin S M. Use of Patterns for Detection of Likely Answer Strings: A Systematic Approach//Proc of the 11 th Text Retrieval Conference. Gaithersbarg, USA, 2001 : 175 - 182.
  • 3崔桓,蔡东风,苗雪雷.基于网络的中文问答系统及信息抽取算法研究[J].中文信息学报,2004,18(3):24-31. 被引量：46
  • 4Danilo G, Bemardo M, Ido D, et al. The Third PASCAL Recognizing Textual Entailment Challenge//Proc of the Workshop on Textual Entailment and Paraphrasing. Prague, Czech Republic, 2007: 1-9.
  • 5Breck E, Burger J, Ferro L, et al. How to Evaluate Your Question Answering System Every Day and Still Get Real Work Done///Proc of the 2nd Conference on Language Resources and Evaluation. Athens, Greece, 2000 : 1495 - 1500.
  • 6Sleator D D K, Temperley D. Parsing English with a Link Grammar. Technical Report, CMU-CS-91-196, Pittsburgh, USA: Carnegie Mellon University. Department of Computer Science, 1991.
  • 7杜永萍,黄萱菁,吴立德.模式学习在QA系统中的有效实现[J].计算机研究与发展,2006,43(3):449-455. 被引量：10
  • 8Ravichandran D, Hovy E. Learning Surface Text Patterns for a Question Answering System//Proc of the 40th Annual Meeting of the Association for Computational Linguistics. Philadelphia, USA, 2002:41 -47.

二级参考文献17

  • 1E.Voorhees.Overview of the TREC-9 Question Answering Track [A].In:Proceedings of the 9th Text Retrieval Conference (TREC9)[C],NIST,Gaithersburg,MD,2000,71-80.
  • 2C.Kwok,O.Etzioni,and D.S.Weld.Scaling Question Answering to the Web [A].In:Proceedings of the 10th World Wide Web Conference (WWW2001)[C],Hong Kong,2001,150-161.
  • 3Dell Zhang,Wee Sun Lee.A Web-based Question Answering System[A].In:Proceedings of the SMA Annual Symposium 2003 [C],NUS,Singapore,Jan 2003.
  • 4Long Hao,Cai Dongfeng.A Word-maching-based Method of Computing the Degree of Similarity Between Sentences[A].Advance in Computation of Oriental Languages.20th International Conference on Computer Processing of Oriental Languages Shenyang [C],China,August
  • 5崔桓 蔡东风 苗雪雷.问答系统中疑问句理解的分析研究[A]..中国人工智能进展[C].北京邮电大学出版社,2003,11.1023-1027.
  • 6S.Dumais,M.Banko,E.Brill,J.Lin and A.Ng.Web Question Answering:Is More Always Better? [A].In:proceedings of SIGIR02 [C],Aug 2002,291-298.
  • 7D, Moldovan, S. Harabagiu, R, Girju, et al. LCC tools for question answering. The TREC-11 Conf., NIST, Gaithersburg,MD, 2002.
  • 8J, Prager, J. Chu-Carroll. Use of WordNet hypernyms for answering what is questions. The TREC-10 Conf., NIST,Gaithersburg, MD, 2001.
  • 9E. H. Hovy, U. Hermjakob, C.-Y. Lin. The use of external knowledge in factoid QA. The TREC-10 Conf., NIST,Gaithersburg, MD, 2001.
  • 10D. Ravichandran, E. Hovy. Learning surface text patterns for a question answering system. The 40th Annual Meeting of the Association for Computational Linguistics ( ACL 2002 ),Philadelphia, PA, USA, 2002.

共引文献54

模式识别与人工智能
2009年 第4期

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