Research Article

Automated Text Summarization：a Survey

In-Su Kang

경성대학교

Published: January 2010 · No. 39 · pp. 5-29

DOI: https://doi.org/10.20880/kler.2010..39.5

Abstract

Information that human should read grows exponentially. To deal with this problem, computational linguistics and natural language processing communities have attempted to automate summarizing text. Since its start in 1950’s, automated text summarization has handled single-/multi-document summarization using extracting and abstracting techniques, and nowadays specialized its tasks to query-focused multi- document summarization. This paper gives the current state of automatic text summarization techniques focusing on robust, practical extraction- based methods, and describes evaluation methodologies and large-scale summarization evaluation conferences. Finally, future issues are discussed.

Keywords: 문서 자동 요약추출 요약추상 요약다중 문서 요약요약 평가

REFERENCES (45)

[1]
[1] [학술대회논문] Barzilay, R./Using lexical chains for text summarization/In Proceedings of the ACL/EACL Workshop on Intelligent Scalable Text Summarization/1997//~/ Google Scholar ›
[2]
[2] [학술지(정기간행물)] Baxendale, P./Machine-made index for technical literature-an experiment/IBM Journal of Research and Development/1958/2/354~361// Google Scholar ›
[3]
[3] [학술대회논문] Bossard, A./Description of the lipn systems at TAC 2008：summarizing information and opinions/Proceedings of the Text Analysis Conference/2008//~/ Google Scholar ›
[4]
[4] [학술지(정기간행물)] Brandow, R./Automatic condensation of electronic publications by sentence selection/Information Processing and management/1995/31(5)/675~686// Google Scholar ›
[5]
[5] [학술지(정기간행물)] Brin, S./The anatomy of a large-scale hypertextual Web search engine/Computer Networks and ISDN Systems/1998/30/1~7// Google Scholar ›
[6]
[6] [학술대회논문] Carbonell, J./The use of MMR and diversity-based reranking for reordering documents and producing summaries/Proceedings of SIGIR-1998/1998//335~336/ Google Scholar ›
[7]
[7] [학술대회논문] Conroy, J./Text summarization via hidden markov models/Proceedings of SIGIR/2001//406~407/ Google Scholar ›
[8]
[8] [학술대회논문] Corston-Oliver, S./Task-focused summarisation of email/Proceedings of ACL/2004//43~50/ Google Scholar ›
[9]
[9] [학술대회논문] Dang, H. T./Overview of the TAC 2008 update summarization task/Proceedings of the Text Analysis Conference/2008//10~23/ Google Scholar ›
[10]
[10] [학위논문] DeJong, G./Fast Skimming of News Stories：The FRUMP System/박사/Yale University//1978 Google Scholar ›
[11]
[11] [학술대회논문] duVerle, D./A novel discourse parser based on support vector machine classification/Proceedings of ACL/2009//665~673/ Google Scholar ›
[12]
[12] [학술지(정기간행물)] Edmundson, H./New methods in automatic extracting/Journal of the ACM/1969/16(2)/264~285// Google Scholar ›
[13]
[13] [학술지(정기간행물)] Erkan, G./LexRank：graph-based centrality as salience in text summarisation/Journal of Artificial Intelligence Research/2004/22/457~479// Google Scholar ›
[14]
[14] [단행본] Information extraction：techniques and challenges. in: Information Extraction/Grishman, R./Springer/1997/~/// Google Scholar ›
[15]
[15] [단행본] Cohesion in English/Halliday, M./Longman/1976/~/// Google Scholar ›
[16]
[16] [단행본] Automated text summarization. in: The Oxford Handbook of Computational Linguistics/Hovy, E./Oxford University Press/2005/~/// Google Scholar ›
[17]
[17] [학술대회논문] Hovy, E./Evaluating duc 2005 using basic elements/Proceedings of Document Understanding Conference(DUC)/2005//~/ Google Scholar ›
[18]
[18] [학술대회논문] Katragadda, R./Sentence position revisited：a robust light-weight update summarization baseline algorithm/Proceedings of the International Workshop on Cross Lingual Information Access/2009//46~52/ Google Scholar ›
[19]
[19] [학술지(정기간행물)] Kleinberg, J./Authoritative sources in a hyperlinked environment/Journal of the ACM/1999/46(5)/604~632// Google Scholar ›
[20]
[20] [학술대회논문] Kupiec, J./A trainable document summariser/Proceedings of SIGIR/1995//68~73/ Google Scholar ›
[21]
[21] [학술대회논문] Lin, C./Identifying Topics by Position/Proceedings of ANLP/1997//283~290/ Google Scholar ›
[22]
[22] [학술대회논문] Lin, C./Training a selection function for extraction/Proceedings of CIKM/1999//1~8/ Google Scholar ›
[23]
[23] [학술대회논문] Lin, C./Rouge：a package for automatic evaluation of summaries/Proceedings of ACL/2004//74~81/ Google Scholar ›
[24]
[24] [학술대회논문] Lin, C./An information-theoretic approach to automatic evaluation of summaries/Proceedings of HLT-NAACL/2006//463~470/ Google Scholar ›
[25]
[25] [학술지(정기간행물)] Luhn, H./The automatic creation of literature abstracts/IBM Journal of Research and Development/1958/2/159~165// Google Scholar ›
[26]
[26] [단행본] Advances in automatic text summarisation/Mani, I./MIT Press/1999/~/// Google Scholar ›
[27]
[27] [학술대회논문] Mani, I./The TIPSTER SUMMAC text summarization evaluation/Proceedings of EACL/1999//77~85/ Google Scholar ›
[28]
[28] [학위논문] Marcu, D./The rhetorical parsing, summarization, and generation of natural language texts/박사/University of Toronto//1997 Google Scholar ›
[29]
[29] [학술대회논문] McKeown, K./Generating summaries of multiple news articles/Proceedings of SIGIR/1995//74~82/ Google Scholar ›
[30]
[30] [학술대회논문] Mihalcea, R./Graph-based ranking algorithms for sentence extraction, applied to text summarization/In Proceedings of ACL/2004//~/ Google Scholar ›
[31]
[31] [학술지(정기간행물)] Morris, A./The effects and limitations of automated text condensing on reading comprehension performance/Information Systems Research/1992/3(1)/17~35// Google Scholar ›
[32]
[32] [학술대회논문] Murray, G./Extractive summarisation of meeting recordings/Proceedings of ACL/2005//~/ Google Scholar ›
[33]
[33] [학술대회논문] Nenkova, A./Automatic text summarization of newswire：Lessons learned from the document understanding conference/Proceedings of AAAI/2005//~/ Google Scholar ›
[34]
[34] [학술대회논문] Nobata, C./Evaluation of features for sentence extraction on different types of corpora/Proceedings of ACL/2003//~/ Google Scholar ›
[35]
[35] [학술대회논문] Pitler, E./Easily identifiable discourse relations/Proceedings of COLING/2008//~/ Google Scholar ›
[36]
[36] [학술대회논문] Radev, D./Centroid-based summarisation of multiple documents：sentence extraction, utilitybased evaluation, and user studies/Proceedings of ANLP/NAACL/2000//21~30/ Google Scholar ›
[37]
[37] [학술지(정기간행물)] Salton, G./Automatic text structuring and summarization/Information Processing & Management/1997/33(2)/193~207// Google Scholar ›
[38]
[38] [학술대회논문] Shen, D./Document summarization using Conditional Random Fields/Proceedings of IJCAI/2007//1805~1813/ Google Scholar ›
[39]
[39] [단행본] Evaluating natural language processing systems/Sparck-Jones, K./Springer/1996/~/// Google Scholar ›
[40]
[40] [단행본] Automatic summarising：Factors and directions. in: Advances in automatic text summarisation/Sparck-Jones, K./MIT Press/1999/~/// Google Scholar ›
[41]
[41] [학술대회논문] Sumita, K./A discourse structure analyzer for Japanese text/Proceedings of the International Conference on Fifth Generation Computer Systems/1992/통권 : 2/1133~1140/ Google Scholar ›
[42]
[42] [학술대회논문] Svore, K./Enhancing single-document summarization by combining RankNet and third-party sources/Proceedings of EMNLP- CoNLL/2007//448~457/ Google Scholar ›
[43]
[43] [학술대회논문] Teufel, S./Sentence extraction as a classification task/Proceedings of ACL/1997//58~65/ Google Scholar ›
[44]
[44] [학술지(정기간행물)] Zajic, D./Multi-candidate reduction：Sentence compression as a tool for document summarization tasks/Information Processing and Management/2007/43/1549~1570// Google Scholar ›
[45]
[45] [학술대회논문] Zechner, K./Automatic generation of concise summaries of spoken dialogues in unrestricted domains/Proceedings of SIGIR/2001//199~207/ Google Scholar ›

Publication History

Published 2010-01-01

Metrics

Cited by 2