计算机科学 ›› 2017, Vol. 44 ›› Issue (6): 1-7.doi: 10.11896/j.issn.1002-137X.2017.06.001

• 目次 •    下一篇

基于Web的问答系统综述

李舟军,李水华   

  1. 北京航空航天大学计算机学院 北京100191,北京航空航天大学计算机学院 北京100191
  • 出版日期:2018-11-13 发布日期:2018-11-13
  • 基金资助:
    本文受国家自然科学基金项目(61672081,U1636211),国家863计划项目(2015AA016004),北京成像技术高精尖创新中心项目(BAICIT-2016001)资助

Survey on Web-based Question Answering

LI Zhou-jun and LI Shui-hua   

  • Online:2018-11-13 Published:2018-11-13

摘要: 微软小冰引发了问答系统的新一轮研究热潮。作为一种新型的信息检索方式,问答系统能直接以自然语言与用户进行人性化的交互。而基于Web的问答系统能通过搜索引擎获取开放的互联网上的各种相关信息,并将以自然语言形式表述的准确答案返回给用户,因此此类系统同时具有搜索引擎和问答系统的优点。首先,对基于Web的问答系统的研究背景与发展历史进行了概述;然后,详细介绍了基于Web的问答系统的架构及其问题分析、信息检索、答案抽取这三大关键技术的研究进展;在此基础上,分析了基于Web的问答系统所面临的问题;最后,对基于Web的问答系统的未来发展趋势进行了展望。

关键词: 问答系统,基于Web的问答系统,问题分析,信息检索,答案抽取

Abstract: Microsoft Xiaoice triggers a new round of boom on question answering research.As a new kind of information retrieval technology,question answering offers friendly interaction for users by using natural languages.Web-based question answering extracts answers in natural languages for users’ questions from search results provided by search engines.Web-based question answering has both advantages of search engine and question answering.Firstly,background and history of web-based question answering were summarized.Then,the research progress of the three key technologies of web-based question answering(question analysis,information retrieval and answer extraction) were introduced in detail.Based on the above introduction,the problems to be solved of web-based question answering were analyzed.Finally,the future research trend of web-based question answering was discussed.

Key words: Question answering,Web-based question answering,Question analysis,Information retrieval,Answer extraction

[1] MAO X L,LI X M.A survey on question and answering systems[J].Journal of Frontiers of Computer Science & Technology,2012,6(3):193-207.(in Chinese) 毛先领,李晓明.问答系统研究综述[J].计算机科学与探索,2012,6(3):193-207.
[2] KEYES R W.The impact of Moore’s Law[J].IEEE Solid-State Circuits Newsletter,2006,20(3):25-27.
[3] YANG D,YU K.“Internet+” Epoch Social Management Innovation:Challenge and Response-To the Case of Shanghai Taxi Operations Management[J].International Journal of Social Science Studies,2015,3(6):197-201.
[4] YANG M C,LEE D G,PARK S Y,et al.Knowledge-basedquestion answering using the semantic embedding space[J].Expert Systems with Applications,2015,42(23):9086-9104.
[5] CUI W,XIAO Y,WANG W.KBQA:an Online Template Based Question Answering System over Freebase[C]∥Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence.New York:IJCAI/AAAI Press,2016:4240-4241.
[6] LIU Y,LI S,CAO Y,et al.Understanding and summarizing answers in community-based question answering services[C]∥Proceedings of the 22nd International Conference on Computational Linguistics.Manchester:Coling 2008 Organizing Committee,2008:497-504.
[7] ZHANG K,WU W,WANG F,et al.Learning distributed representations of data in community question answering for question retrieval[C]∥Proceedings of the Ninth ACM International Conference on Web Search and Data Mining.San Francisco:ACM,2016:533-542.
[8] SUN H,WEI F,ZHOU M.Answer Extraction with Multiple Extraction Engines for Web-Based Question Answering[M]∥Natural Language Processing and Chinese Computing.Shenzhen:Springer,2014:321-332.
[9] SU F,GAO D L,YE C.Study on Question Understanding ofWeb-based Question-answering System[J].Journal of Test and Measurement Technology,2012,26(3):207-212.(in Chinese) 苏斐,高德利,叶晨.Web 问答系统中问句理解的研究[J].测试技术学报,2012,26(3):207-212.
[10] TURING A M.Computing machinery and intelligence[J].Mind,1950,59(236):433-460.
[11] GREEN B F,JR,WOLF A K,et al.Baseball:an automatic question-answerer[C]∥Proceedings of the Western Joint Computer Conference.Los Angeles:ACM,1961:219-224.
[12] WOODS W A,KAPLAN R.Lunar rocks in natural English:Explorations in natural language question answering[J].Linguistic Structures Processing,1977,5(1):521-569.
[13] WEIZENBAUMJ.ELIZA-a computer program for the study of natural language communication between man and machine[J].Communications of the ACM,1966,9(1):36-45.
[14] KATZ B.From sentence processing to information access on the world wide web[C]∥AAAI Spring Symposium on Natural Language Processing for the World Wide Web.Stanford:Stanford University,1997:22-25.
[15] ZHENG Z.AnswerBus question answering system[C]∥Proceedings of the Second International Conference on Human Language Technology Research.San Diego:Morgan Kaufmann Publishers Inc.,2002:399-404.
[16] HOVY E H,GERBER L,HERMJAKOB U,et al.Question Answering in Webclopedia[C]∥Proceedings of The Ninth Text REtrieval Conference.Gaithersburg:National Institute of Stan-dards and Technology,2000:53-56.
[17] DRENOYIANNI H,SELWOOD I,RIDING R.Searching Using ‘Microsoft? Encarta?’[J].Education and Information Techno-logies,2002,7(4):333-342.
[18] ZHANG D,LEE W S.Web Based Pattern Mining and Matching Approach to Question Answering[C]∥Proceedings of The Eleventh Text REtrieval Conference.Gaithersburg:National Institute of Standards and Technology,2002:129-144.
[19] STEPHEN.Wolfram Language Artificial Intelligence:The Image Identification Project[EB/OL].http://blog.stephenwolf-ram.com/2015/05/wolfram-language-artificial-intelligence-the-ima-ge-identification-project.
[20] FIVEASH K.Wolfram Alpha given keys to the Bingdom[EB/OL].http://www.theregister.co.uk/2009/11/12/bing_wolfram_alpha_deal.
[21] VOLKMER T,SMITH J R,NATSEV A P.A web-based system for collaborative annotation of large image and video collections:an evaluation and user study[C]∥Proceedings of the 13th annual ACM international conference on Multimedia.Singapore:ACM,2005:892-901.
[22] SCOBLEIZER.BREAKING NEWS:Siri bought by Apple[EB/OL].http://scobleizer.com/2010/04/28/breaking-news-siri-bought-by-apple.
[23] 麒麟会.微软亚洲互联网工程院将分享“小冰”背后的故事[EB/OL].http://tech.ifeng.com/a/20140928/40825530_0.shtml.
[24] 凤凰网.就在今晚!百度机器人将大战“最强大脑”选手[EB/OL].http://ent.ifeng.com/a/20170106/42804563_0.shtml?_zbs_baidu_bk.
[25] KWOK C,ETZIONI O,WELD D S.Scaling question answering to the web[J].ACM Transactions on Information Systems,2001,19(3):242-262.
[26] WANG M.A survey of answer extraction techniques in factoid question answering[J].Computational Linguistics,2006,1(1):1-14.
[27] YANG H,CHUA T S.Effectiveness of web page classification on finding list answers[C]∥Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval.Sheffield:ACM,2004:522-523.
[28] GONALVES P N,BRANCO A.Open-domain web-based listquestion answering with LX-listquestion[C]∥Proceedings of the 4th International Confe-rence on Web Intelligence,Mining and Semantics.Thessaloniki:ACM,2014:43-49.
[29] GONALVES P N,BRANCO A H.A Comparative Evaluation of QA Systems over List Questions[C]∥International Confe-rence on Computational Processing of the Portuguese Language.Tomar:Springer,2016:115-121.
[30] REN H,JI D,TENG C,et al.A web knowledge based approach for complex question answering[C]∥Asia Information Retrieval Symposium.Dubai:Springer,2011:470-478.
[31] SAVENKOV D.Ranking Answers and Web Passages for Non-factoid Question Answering:Emory University at TREC LiveQA[C]∥Proceedings of The Twenty-Fourth Text REtrie-val Conference.Gaithersburg:National Institute of Standards and Technology,2015:1-8.
[32] MOSCHITTI A,MáRQUEZ L,NAKOV P,et al.SIGIR 2016 Workshop WebQA II:Web Question Answering Beyond Factoids[C]∥Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval.Pisa:ACM,2016:1251-1252.
[33] AGICHTEIN E,CARMEL D,CLARKE C L A,et al.Webquestion answering:Beyond factoids:SIGIR 2015 workshop[C]∥Proceedings of the 38th International ACM SIGIR Confe-rence on Research and Development in Information Retrieval.Santiago:ACM,2015:1143-1143.
[34] QUARTERONI S,MANANDHAR S.Designing an interactive open-domain question answering system[J].Natural Language Engineering,2009,15(1):73-95.
[35] LI S,LIN C Y,SONG Y I,et al.Comparable entity mining from comparative questions[J].IEEE Transactions on Knowledge and Data Engineering,2013,25(7):1498-1509.
[36] YIH W,MA H.Question Answering with Knowledge Base,Web and Beyond[C]∥Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval.Pisa:ACM,2016:1219-1221.
[37] WU G S,LAN M.Leverage Web-based Answer Retrieval and Hierarchical Answer Selection to Improve the Performance of Live Question Answering[C]∥Proceedings of The Twenty-Fourth Text REtrieval Conference.Gaithersburg:National Institute of Standards and Technology,2015:1-8.
[38] CAO Z J,LI Z S,LIU C T.Study of Question Analysis in Question-Answering System[J].Computer Science,2005,32(11):158-160.(in Chinese) 曹志娟,李祖枢,刘朝涛.自动问答系统中的问题理解研究[J].计算机科学,2005,32(11):158-160.
[39] LI X,ROTH D.Learning question classifiers:the role of semantic information[J].Natural Language Engineering,2006,12(3):229-249.
[40] WEN X,ZHANG Y,LIU T,et al.Syntactic Structure Parsing Based Chinese Question Classification [J].Journal of Chinese Information Processing,2006,20(2):35-41.(in Chinese) 文勖,张宇,刘挺,等.基于句法结构分析的中文问题分类[J].中文信息学报,2006,20(2):35-41.
[41] LIU Z J,WANG X L,CHEN Q C,et al.A Chinese question answering system based on Web search[C]∥International Confe-rence on Machine Learning and Cybernetics.Lanzhou:IEEE,2014:816-820.
[42] LI X,HU D,LI H,et al.Automatic question answering fromWeb documents[J].Wuhan University Journal of Natural Scie-nces,2007,12(5):875-880.
[43] ZHANG Z C,ZHANG Y,LIU T,et al.Advances in open-domain question answering[J].Acta Electronica Sinica,2009,37(5):1058-1069.(in Chinese) 张志昌,张宇,刘挺,等.开放域问答技术研究进展[J].电子学报,2009,37(5):1058-1069.
[44] ZHANG D,LEE W S.Question classification using support vector machines[C]∥Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval.Toronto:ACM,2003:26-32.
[45] CHALI Y,HASAN S A,MOJAHID M.A reinforcement lear-ning formulation to the complex question answering problem[J].Information Processing & Management,2015,51(3):252-272.
[46] SUZUKI J,TAIRA H,SASAKI Y,et al.Question classification using HDAG kernel[C]∥Proceedings of the ACL 2003 Workshop on Multilingual Summarization and Question Answering.Sapporo:ACL,2003:61-68.
[47] MOSCHITTI A,QUARTERONI S,BASILI R,et al.Exploiting syntactic and shallow semantic kernels for question answer classification[C]∥Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics.Prague:ACL,2007:776-783.
[48] POTA M,ESPOSITO M,DE P G.A Forward-Selection Algorithm for SVM-Based Question Classification in Cognitive Systems[M].Switzerland:Springer,2016:587-598.
[49] MCROY S,JONES S,KURMALLY A.Toward automated classification of consumers’ cancer-related questions with a new taxonomy of expected answer types[J].Health Informatics Journal,2016,22(3):523-535.
[50] YANG M H,AHUJA N.Learning to Detect Faces with Snow[M]∥Face Detection and Gesture Recognition for Human-Computer Interaction.2001:123-150.
[51] LI X,ROTH D.Learning question classifiers:the role of semantic information[J].Natural Language Engineering,2006,12(3):229-249.
[52] MERKEL A,KLAKOW D.Language model based query classification[C]∥Advances in Information Retrieval.Rome:Springe,2007:720-723.
[53] LIN S J,LU W H.Learning question focus and semantically related features from web search results for chinese question classification[C]∥The Third Asia Information Retrieval Sympo-sium.Singapore:Springer,2006:284-296.
[54] ANAND K M,SOMAN K P.Amrita_CEN@ MSIR-FIRE2016:Code-Mixed Question Classification using BoWs and RNN Embeddings[C]∥Working notes of Forum for Information Retrie-val Evaluation.Kolkata:CEUR-WS,2016:122-125.
[55] MOLDOVAN D,HARABAGIU S,PASCA M,et al.The structure and performance of an open-domain question answering system[C]∥The 38th Annual Meeting of the Association for Computational Linguistics.Hong Kong:ACL,2000:563-570.
[56] BRILL E,DUMAIS S,BANKO M.An analysis of the AskMSR question-answering system[C]∥Proceedings of the ACL-02 Conference on Empirical Methods in Natural Anguage.Stroudsburg:ACL,2002:257-264.
[57] BRILL E,LIN J J,BANKO M,et al.Data-Intensive Question Answering[C]∥Proceedings of The Tenth Text REtrieval Conference.Gaithersburg:National Institute of Standards and Technology,2001:393-400.
[58] GONALVES P N,BRANCO A.Answering List Questions using Web as a corpus[C]∥Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics.Gothenburg:ACL,2014:81-84.
[59] SUN H,MA H,YIH W,et al.Open domain question answering via semantic enrichment[C]∥Proceedings of the 24th International Conference on World Wide Web.Florence:ACM,2015:1045-1055.
[60] SEVERYN A,MOSCHITTI A.Automatic Feature Engineering for Answer Selection and Extraction[C]∥Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing.Seattle:ACL,2013:458-467.
[61] YAO X,VAN Durme B,CALLISON B C,et al.Answer Extraction as Sequence Tagging with Tree Edit Distance[C]∥Human Language Technologies:Conference of the North American Chapter of the Association of Computational Linguistics.Atlanta:ACL,2013:858-867.
[62] SREELAKSHMI V,JAMAL S.Web Based Question Answering System using Pattern Matching[C]∥The International Confe-rence on Information Science.Pattaya:IEEE,2015:1-4.
[63] CHU CARROLL J,FAN J.Leveraging Wikipedia Characteristics for Search and Candidate Generation in Question Answering[C]∥Proceedings of the Twenty-Fifth AAAI Conference on Artificial Intelligence.San Francisco:AAAI Press,2011:872-877.
[64] XU J,LICUANAN A,MAY J,et al.Answer Selection and Confidence Estimation[C]∥New Directions in Question Answe-ring.Stanford:AAAI Press,2003:134-137.
[65] ZHANG D,LEE W S.Web Based Pattern Mining and Matching Approach to Question Answering[C]∥Proceedings of The Eleventh Text REtrieval Conference.Gaithersburg:National Institute of Standards and Technology,2002:129-141.
[66] MEDITSKOS G,DASIOPOULOU S,VROCHIDIS S,etal.Question Answering over Pattern-Based User Models[C]∥Proceedings of the 12th International Conference on Semantic Systems.Leipzig:ACM,2016:153-160.
[67] YU Z T,FAN X Z,GUO J Y,et al.Answer extracting for chinese question-answering system based on latent semantic analysis[J].Chinese Journal of Computer,2006,29(10):1889-1893.(in Chinese) 余正涛,樊孝忠,郭剑毅,等.基于潜在语义分析的汉语问答系统答案提取[J].计算机学报,2006,29(10):1889-1893.
[68] DEERWESTER S,DUMAIS S T,FURNAS G W,et al.Indexing by latent semantic analysis[J].Journal of the American Society for Information Science,1990,41(6):391.
[69] SUN H,DUAN N,DUAN Y,et al.Answer Extraction fromPassage Graph for Question Answering[C]∥Proceedings of the 23rd International Joint Conference on Artificial Intelligence.Beijing:IJCAI/AAAI,2013:2169-2175.
[70] FIGUEROA A G,NEUMANN G.Genetic algorithms for data-driven web question answering[J].Evolutionary Computation,2008,16(1):89-125.
[71] KHODADI I,ABADEH M S.Genetic programming-based fea-ture learning for question answering[J].Information Processing & Management,2016,52(2):340-357.
[72] MA Y J,YUN W X.Research progress of genetic algorithm[J].Application Research of Computers,2012,29(4):1201-1206.(in Chinese) 马永杰,云文霞.遗传算法研究进展[J].计算机应用研究,2012,29(4):1201-1206.
[73] MA C L,YAN Y H.Short Text Classification Based on Probabilistic Semantic Distribution[J].Acta Automatica Sinica,2016,42(11):1711-1717.(in Chinese) 马成龙,颜永红.基于概率语义分布的短文本分类[J].自动化学报,2016,42(11):1711-1717.
[74] MA L.The Research and Implementation of Web-based Chinese Question Answering System[D].Beijing:Beihang University,2012.(in Chinese) 马琳.基于Web的中文问答系统的研究与实现[D].北京:北京航空航天大学,2012.
[75] LEE J,KIM G,YOO J,et al.Training IBM Watson using Automatically Generated Question-Answer Pairs[C]∥The 50th Hawaii International Conference on System Sciences.Hawaii:AIS Electronic Library,2017:1-9.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!