面向限定领域问答系统的自然语言理解方法综述

doi:10.11896/j.issn.1002-137X.2017.08.001

摘要/Abstract

摘要： 领域无关的自然语言理解(NLU)技术在最近的十年中取得了长足的进步,然而由于基础研究与现实应用之间存在着强烈的实际需求与当前处理能力不足的矛盾,因此很多通用技术还不能在现实的问答系统中得到有效使用。针对现有的需求,开发面向领域的自然语言理解技术显得非常必要。首先对开放领域与限定领域问答系统进行了比较,并对一些典型的面向限定领域问答系统的自然语言理解技术进行了分析,然后介绍了面向限定领域问答系统的自然语言理解技术的评测标准,最后总结了目前限定领域问答系统研究存在的主要问题及未来发展方向。

关键词: 限定领域,问答系统,自然语言理解,评测

Abstract: Natural language understanding (NLU) in the last decade has made considerable progress in the line of domain-independent research.Such research is very important,but the gap between research results and real-world applications is large,and the strong realistic demand is in contradiction with the current processing capacity of the NLU community,which makes the development of domain-specific NLU technologies very necessary.We firstly compared open domain and domain specific question answering(QA) system.Then some typical natural language understanding technologies used in restricted domain question answering system were detailedly analyzed.The evaluation standard of the natural language understanding technology for domain-specific question answering system was introduced.At last,main problems and the future development of domain specific QA system were summarized.

Key words: Domain-specific,Question answering system,NLU,Evaluation

王东升,王卫民,王石,符建辉,诸峰. 面向限定领域问答系统的自然语言理解方法综述[J]. 计算机科学, 2017, 44(8): 1-8. https://doi.org/10.11896/j.issn.1002-137X.2017.08.001

WANG Dong-sheng, WANG Wei-min, WANG Shi, FU Jian-hui and ZHU Feng. Research on Domain-specific Question Answering System Oriented Natural Language Understanding:A Survey[J]. Computer Science, 2017, 44(8): 1-8. https://doi.org/10.11896/j.issn.1002-137X.2017.08.001

参考文献

[1] WOODS W A.Conceptual indexing:A better way to organizeknowledge:Technical Report SMLI TR-97-61[R].Sun Microsystems,Inc.,1997.
[2] GREEN J,BERT F,et al.Baseball:an automatic question-answerer[C]∥Proceedings Western Computing Conference,1961.ACM,1961:219-224.
[3] FERRUCCI D,BROWN E,CHU-CARROLL J,et al.BuildingWatson:An overview of the Deep QA project[J].AI Magazine,2010,31(3):59-79.
[4] FRASER N,DALSGAARD P.Spoken Dialogue System:A European Perspective[C]∥Proc.Int’l Symp.Spoken Dialogue.1996:25-36.
[5] 宗成庆.统计自然语言处理[M].北京:清华大学出版社,2008.
[6] WILENSKY R,CHIN D N,LURIA M,et al.The BerkeleyUnix Consultant project[J].Computational Linguistics,1994,14(4):35-84.
[7] CARPENTER B,CHU-CARROLL J.Natural language call routing:A robust,self-organized approach[C]∥Proc.Int.Conf.Spoken Language Proc..1998:2059-2062.
[8] BRILL E,LIN J J,BANKO M,et al.Data-Intensive Question Answering[C]∥TREC.2001:90.
[9] MOLL D,VICEDO J L.Question answering in restricted domains:An overview[J].Computational Linguistics,2007,33(1):41-61.
[10] MOLDOVAN D,RUS V.Logic Form Transformation of WordNet and its Applicability to Question Answering[C]∥Procee-dings of 37th Meeting of Association of Computational Linguistics (ACL’2001).2001.
[11] ADROUTSOPOULOS I,RITCHIE G D,T HANISCH P.Natural Language Interfaces to Databases:An Introduction[J].Journal of Natural Language Engineering,1995,1(1):29-81.
[12] UNOLD O,DABROWSKI G.Use of learning classifier system for inferring natural language grammar[M]∥Learning Classi-fier Systems.Springer Berlin Heidelberg,2007:17-24.
[13] KOZAREVA Z,HOVY E.Tailoring the automated construction of large-scale taxonomies using the Web[J].Language Resources and Evaluation,2013,47(3):859-890.
[14] ZETTLEMOYER L S,COLLINS M.Learning to map sentences to logical form:Structured classification with probabilistic categorial grammars[C]∥ Proceedings of the 21st Conference on Uncertainty in AI.2005:658-666.
[15] ANDRENUCCI A,SNEIDERS E.Automated Question Ans-wering:Review of the Main Approaches[C]∥ICITA (1).2005:514-519.
[16] BINOT J L,et al.Natural language interfaces:a new philosophy[J].Sun Expert Magazine,1991.
[17] OTT N.Aspects of the Automatic Generation of SQL state-ments in a Natural Language Query Interface[J].Information Systems,1992,17(2):147-159.
[18] MOLLA D,et al.NLP for Answer Extraction in Technical Domains[C]∥Proc.of EACL 2003.Morgan Kaufmann,USA,2003.
[19] WANG Y Y,DENG L,ACERO A.Semantic Frame-Based Spoken Language Understanding[J].Spoken Language Understanding:Systems for Extracting Semantic Information from Speech,2011,48(3):41-91.
[20] FENG Z W.Complex Features in Description of Chinese Lan-guage[J].Journal of Chinese Information Processing,1990,4(3):20-29.(in Chinese) 冯志伟.汉语句子描述中的复杂特征[J].中文信息学报,1990,4(3):20-29.
[21] BURTON R R.Semantic Grammar:An Engineering Technique for Constructing Natural Language Understanding Systems[J].ACM Sigart Bulletin,1976(61):26.
[22] WALTZ D L.An english language question answering system for a large relational database[J].Communications of the ACM,1978,1(7):526-539.
[23] HENDRIX G,SACERDOTI E,S AGALOWICZ D,et al.Developing a natural language interface to complex data[J].ACM Transactions on Database System,1978,3(2):105-147.
[24] THOMPSON F B,THOMPSON B H.Practial natural language processing:the REL system prototype[J].Advances in Compu-ters,1975,13:109-168.
[25] TEMPLETON M,BURGER J.Problems in Natural language in- terface to DBMS with examples from EUFID[C]∥Proceedings of the 1st Conference on Applied Natural Language Processing.Santa Monica,California,1983:3-16.
[26] WANG Y Y,ACERO A.Rapid development of spoken language understanding grammars[J].Speech Communication,2006,48(3):390-416.
[27] SENEFF S.TINA:A Natural Language System for SpokenLanguage Applications[J].Computational Linguistics,1992,18(1):61-86.
[28] FRANCEZ N,WINTNER S.Unification Grammars[M].New York:Cambridge University Press,2012.
[29] WARD W,ISSAR S.Recent improvements in the CMU spoken language understanding system[C]∥Proc.ARPA Human Language Technology.1996:213-216.
[30] SHAPIRO S C.Generalized augmented transition network gram-mars for generation from semantic networks[J].Computational Linguistics,1982,8(1):12-25.
[31] PIERACCINI R,LUBENSKY D.Spoken language communication with machines:the long and winding road from research to business[C]∥International Conference on Industrial,Enginee-ring and Other Applications of Applied Intelligent Systems.Springer Berlin Heidelberg,2005:6-15.
[32] PSAROLOGOU A.A Stochastic Petri Net based NLU Scheme for Technical Documents Understanding[D].Wright State University,2016.
[33] WONG Y W,MOONEY R J.Learning for semantic parsingwith statistical machine translation[C]∥Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computatio-nal Linguistics.Association for Computational Linguistics,2006:439-446.
[34] HE Y,YOUNG S.Semantic processing using the hidden vector state model[J].Computer Speeech and Language,2005,9(1):85-106.
[35] MENG H M,WAI C,PIERACCINI R.The use of belief net-works for mixed-initiative dialog modeling[J].IEEE Transactions on Speech and Audio Processing,2003,11(6):757-773.
[36] WU W L,LU R Z,DUAN J Y,et al.Spoken language understanding using weakly supervised learning[J].Computer Speech &Language,2010,24(2):358-382.
[37] MINKER W,WAIBEL A,MARIANI J.Stochastically-based se-antic analysis[J].Springer International,1999,3(2):177-194.
[38] PIERACCINI R.Spoken language understanding,the research/industry chasm[C]∥HLT/NAACL Workshop on Spoken Language Understanding for Conversational Systems.Boston,2004.
[39] WANG Y Y,ACERO A.SGStudio:rapid semantic grammar development for spoken language understanding[C]∥INTERSPEECH.2005:1869-1872.
[40] SCHAPIRE R E,ROCHERY M,RAHIM M,et al.Boosting withprior knowledge for call classification[J].IEEE Transactions on Speech and Audio Processing,2005,13(2):174-181.
[41] RAYNER M,HOCKEY B A.Transparent combination of rule-based and data-driven approaches in a speech understanding architecture[C]∥Proceedings of the Tenth Conference on European Chapter of the Association for Computational Linguistics.Budapest,Hungary,2003:12-17.
[42] WANG Y,MAHAJAN M,HUANG X.A unified context-freegrammar and n-gram model for spoken language processing[C]∥International Conference of Acoustics,Speech,and Signal Processing.Istanbul,Turkey,2000:1639-1642.
[43] WANG D S.A domain-specific question answering system basedon ontology and question templates[C]∥2010 11th ACIS International Conference on Software Engineering Artificial Intelligence Networking and Parallel/Distributed Computing (SNPD).IEEE,2010:151-156.
[44] WANG D S,WANG S,WANG W M,et al.Interactive question answering based on Ontology and semantic Grammar[J].Journal of Chinese Information Processing,2016,2(2):142-152.(in Chinese) 王东升,王石,王卫民,等.基于本体和语义文法的上下文相关问答[J].中文信息学报,2016,2(2):142-152.
[45] DUTA N.Natural Language Understanding and Prediction:from Formal Grammars to Large Scale Machine Learning[J].Fundamenta Informaticae,2014,131(3):425-440.
[46] WANG Y Y.Strategies for statistical spoken language under-standing with small amount of data-an empirical study[C]∥INTERSPEECH-2010.2010:2498-2501.
[47] WANG Y Y,LEE J,MAHAJAN M,et al.Combining statistical and knowledge-based spoken language understanding in conditional models[C]∥Proceedings of the Annual Meeting of the Association for Computational Linguistics.Association for Computational Linguistics,2006:882-889.
[48] KLASINAS I,POTAMIANOS A,IOSIF E,et al.Web data harvesting for speech understanding grammar induction[C]∥INTERSPEECH.2013:2733-2737.
[49] GEMMEKA J F,VAN DE LOO J,DE PAUW G,et al.A Self-Learning Assistive Vocal Interface Based on Vocabulary Lear-ning and Grammar Induction[C]∥Interspeech.2012:831-834.
[50] VAN DE LOO J,DE PAUW G,G EMMEKE J F,et al.Towards shallow grammar induction for an adaptive assistive vocal interface:a concept tagging approach[C]∥Natural Language Processing for Improving Textual Accessibility (NLP4ITA) Workshop Programme.2012:27.
[51] PALOGIANNIDI E,KLASINAS I,POTAMIANOS A,et al.Spoken dialogue grammar induction from crowdsourced data[C]∥2014 IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP).IEEE,2014:3211-3215.
[52] GEORGILADAKIS S,UNGER C,IOSIF E,et al.Fusion ofknowledge-based and data-driven approaches to grammar induction[C]∥Interspeech.2014:288-292.
[53] CHORIANOPOULOU A,ATHANASOPOULOU G,IOSIF E,et al.tucSage:Grammar Rule Induction for Spoken Dialogue Systems via Probabilistic Candidate Selection[C]∥SemEval 2014.2014:668.
[54] GASPERS J,CIMIANO P,WREDE B.Semantic parsing of spee-ch using grammars learned with weak supervision[C]∥Confe-rence of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies (NAACL-HLT).2015.
[55] PARGELLIS A,FOSLER-LUSSIER E,LRR C H,et al.Auto-induced semantic classes[J].Speech Communication,2004,43(3):183-203.
[56] PANGOS A,IOSIF E,POTAMIANOS A,et al.Combining statistical similarity measures for automatic induction of semantic classes[C]∥IEEE Workshop on Auto-matic Speech Recognition and Understanding (2005).IEEE,2005:278-283.
[57] PALOGIANNIDI E.Using crowdsourcing for grammar induc-tion with application to spoken dialogue systems[D].Technical University of Crete,2013.
[58] KAISER E C,JOHNSTON M,HEEMAN P A.Profer:Predictive,robust finite-state parsing for spoken language[C]∥IEEE International Conference on Acoustics,Speech,and Signal Processing,1999.IEEE,1999:629-632.
[59] DIEKERMA A R,YILMAZEL O,LIDDY E D.Evaluation of restricted domain question-answering systems[C]∥ Proceedings of the ACL Workshop on Question Aaswering in Restricted Domains.2004.
[60] FERRUCCI D,LEVAS A,BAGCHI S,et al.Watson:beyond jeopardy![J].Artificial Intelligence,2013,199:93-105.
[61] LOPEZ V,FERNNDEZ M,MOTTA E,et al.Poweraqua:Supporting users in querying and exploring the semantic Web[J].Semantic Web,2012,3(3):249-265.
[62] LOPEZ V,UREN V,SABOU M,et al.Is question answering fit for the semantic web?:a survey[J].Semantic Web,2011,2(2):125-155.
[63] BENAMARA F.Cooperative question answering in restricted do-mains:the WEBCOOP experiment[C]∥Proceedings of the Workshop Question Answering in Restricted Domains.ACL,2004:21-26.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed