Automatic Text Summarization: Past, Present and Future

  • Horacio Saggion
  • Thierry Poibeau
Part of the Theory and Applications of Natural Language Processing book series (NLP)


Automatic text summarization, the computer-based production of condensed versions of documents, is an important technology for the information society. Without summaries it would be practically impossible for human beings to get access to the ever growing mass of information available online. Although research in text summarization is over 50 years old, some efforts are still needed given the insufficient quality of automatic summaries and the number of interesting summarization topics being proposed in different contexts by end users (“domain-specific summaries”, “opinion-oriented summaries”, “update summaries”, etc.). This paper gives a short overview of summarization methods and evaluation.


Text Summarization Reference Summary Automatic Summarization Coherent Text Maximal Marginal Relevance 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



Horacio Saggion is grateful to a fellowship from Programa Ramón y Cajal, Ministerio de Ciencia e Innovación, Spain. Thierry Poibeau is supported by the “Empirical Fundations of Linguistics” labex, Sorbonne-Paris-Cité. We acknowledge the support from the editors of this volume.


  1. 1.
    Barzilay, R.: Modeling local coherence: an entity-based approach. In: Proceedings of ACL 2005, Michigan, pp. 141–148. Association for Computational Linguistics, Stroudsburg (2005)Google Scholar
  2. 2.
    Barzilay, R., Elhadad, M.: Using lexical chains for text summarization. In: Proceedings of the ACL/EACL’97 Workshop on Intelligent Scalable Text Summarization, Madrid, pp. 10–17 (1997)Google Scholar
  3. 3.
    Barzilay, R., Elhadad, N., Mckeown, K.R.: Inferring strategies for sentence ordering in multidocument news summarization. J. Artif. Intell. Res. 17, 2002 (2002)Google Scholar
  4. 4.
    Barzilay, R., Lapata, M.: Modeling local coherence: an entity-based approach. Comput. Linguist. 34(1), 1–34 (2008)Google Scholar
  5. 5.
    Benbrahim, M., Ahmad, K.: Text summarisation: the role of lexical cohesion analysis. In: The New Review of Document and Text Management, pp. 321–335. Taylor Graham Pub., London, UK (1995)Google Scholar
  6. 6.
    Bossard, A., Généreux, M., Poibeau, T.: Cbseas, a summarization system – integration of opinion mining techniques to summarize blogs. In: Proceedings of the 12th Meeting of the European Association for Computational Linguistics (system demonstration), EACL ’09, Athens. Association for Computational Linguistics, Stroudsburg (2009)Google Scholar
  7. 7.
    Carbonell, J.G., Goldstein, J.: The use of MMR, diversity-based reranking for reordering documents and producing summaries. In: Research and Development in Information Retrieval, pp. 335–336. The Association for Computing Machinery, New York (1998)Google Scholar
  8. 8.
    Chambers, N., Jurafsky, D.: Unsupervised learning of narrative schemas and their participants. In: ACL/AFNLP, Singapore, pp. 602–610. Association for Computational Linguistics, Stroudsburg (2009)Google Scholar
  9. 9.
    Cohn, T., Lapata, M.: Sentence compression as tree transduction. J. Artif. Intell. Res. (JAIR) 34, 637–674 (2009)Google Scholar
  10. 10.
    Dang, H.T., Owczarzak, K.: Overview of the tac 2008 opinion question answering and summarization tasks. In: Proceedings of the TAC 2008 Workshop, Notebook Papers and Results, Gaithersburg, MD, USA. NIST, Gaithersburg, MD, USA (2008)Google Scholar
  11. 11.
    DeJong, G.: An overview of the FRUMP system. In: Lehnert, W., Ringle, M. (eds.) Strategies for Natural Language Processing, pp. 149–176. Lawrence Erlbaum Associates, Hillsdale (1982)Google Scholar
  12. 12.
    Edmundson, H.: New methods in automatic extracting. J. Assoc. Comput. Mach. 16(2), 264–285 (1969)Google Scholar
  13. 13.
    Endres-Niggemeyer, B.: SimSum: an empirically founded simulation of summarizing. Inf. Process. Manag. 36, 659–682 (2000)Google Scholar
  14. 14.
    Erkan, G., Radev, D.: Lexrank: graph-based lexical centrality as salience in text summarization. J. Artif. Intell. Res. (JAIR) 22, 457–479 (2004)Google Scholar
  15. 15.
    Fellbaum, C. (ed.): WordNet: An Electronic Lexical Database. MIT, Cambridge (1998)Google Scholar
  16. 16.
    Grishman, R.: Information extraction: techniques and challenges. In: Pazienza, M.T. (ed.) Information Extraction. A Multidisciplinary Approach to an Emerging Information Technology. Lecture Notes in Artificial Intelligence, vol. 1299. Springer, Berlin/New York (1997)Google Scholar
  17. 17.
    Harman, D., Liberman, M.: Tipster Complete. Technical Report, University of Pennsylvania, Philadelphia, USA (1993)Google Scholar
  18. 18.
    Hasler, L., Orãsan, C., Mitkov, R.: Building better corpora for summarisation. In: Proceedings of Corpus Linguistics, Lancaster, pp. 309–319 (2003)Google Scholar
  19. 19.
    Hovy, E., Lin, C.Y., Zhou, L., Fukumoto, J.: Automated summarization evaluation with basic elements. In: Proceedings of the Fifth Conference on Language Resources and Evaluation (LREC), Genoa, Italy. ELDA, Paris, France (2006)Google Scholar
  20. 20.
    Jing, H.: Using hidden markov modeling to decompose human-written summaries. Comput. Linguist. 28, 527–543 (2002)Google Scholar
  21. 21.
    Jing, H., McKeown, K.: The decomposition of human-written summary sentences. In: Hearst, M., Gey, F., Tong, R. (eds.) Proceedings of SIGIR’99 – 22nd International Conference on Research and Development in Information Retrieval, University of California, Berkeley, pp. 129–136 (1999)Google Scholar
  22. 22.
    Jing, H., McKeown, K.: Cut and paste based text summarization. In: Proceedings of the 1st Meeting of the North American Chapter of the Association for Computational Linguistics, Seattle, pp. 178–185. Association for Computational Linguistics, Stroudsburg (2000)Google Scholar
  23. 23.
    Jones, K.S.: Automatic summarising: the state of the art. Inf. Process. Manage. 43(6), 1449–1481 (2007)Google Scholar
  24. 24.
    Kabadjov, M.A., Atkinson, M., Steinberger, J., Steinberger, R., der Goot, E.V.: Newsgist: a multilingual statistical news summarizer. In: ECML/PKDD (3), Barcelona, pp. 591–594. Springer, Berlin/New York (2010)Google Scholar
  25. 25.
    Knight, K., Marcu, D.: Statistics-based summarization – step one: sentence compression. In: Proceedings of the 17th National Conference of the American Association for Artificial Intelligence, Austin. AAAI, Palo Alto, CA, USA (2000)Google Scholar
  26. 26.
    Kupiec, J., Pedersen, J., Chen, F.: A trainable document summarizer. In: Proceedings of the 18th ACM-SIGIR Conference, Seattle, pp. 68–73. ACM, New York (1995)Google Scholar
  27. 27.
    Lapata, M.: Probabilistic text structuring: experiments with sentence ordering. In: Proceedings of the 41st Meeting of the Association of Computational Linguistics, Sapporo, pp. 545–552. Association for Computational Linguistics, Stroudsburg (2003)Google Scholar
  28. 28.
    Li, P., Jiang, J., Wang, Y.: Generating templates of entity summaries with an entity-aspect model and pattern mining. In: Proceedings of ACL, Uppsala. Association for Computational Linguistics, Uppsala (2010)Google Scholar
  29. 29.
    Liddy, E.D.: The discourse-level structure of empirical abstracts: an exploratory study. Inf. Process. Manag. 27(1), 55–81 (1991)Google Scholar
  30. 30.
    Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Proceedings of the Workshop on Text Summarization Branches Out (WAS 2004), Barcelona (2004)Google Scholar
  31. 31.
    Lin, C., Hovy, E.: Identifying topics by position. In: Fifth Conference on Applied Natural Language Processing, Washington, DC, pp. 283–290. Association for Computational Linguistics, Stroudsburg (1997)Google Scholar
  32. 32.
    Lin, C.Y., Hovy, E.: The automated acquisition of topic signatures for text summarization. In: Proceedings of the COLING Conference, Saarbrumlcken. Association for Computational Linguistics, Stroudsburg (2000)Google Scholar
  33. 33.
    Lloret, E., Palomar, M.: Text summarisation in progress: a literature review. Artif. Intell. Rev. 37(1), 1–41 (2011)Google Scholar
  34. 34.
    Louis, A., Nenkova, A.: Automatically evaluating content selection in summarization without human models. In: Proceedings of EMNLP’09, Singapore, pp. 306–314. Association for Computational Linguistics, Stroudsburg (2009)Google Scholar
  35. 35.
    Luhn, H.P.: The automatic creation of literature abstracts. IBM J. Res. Dev. 2(2), 159–165 (1958)Google Scholar
  36. 36.
    Mani, I.: Automatic Text Summarization. John Benjamins, Amsterdam/Philadelphia (2001)Google Scholar
  37. 37.
    Mani, I., Klein, G., House, D., Hirschman, L., Firmin, T., Sundheim, B.: Summac: a text summarization evaluation. Nat. Lang. Engin. 8, 43–68 (2002). DOI 10.1017/S1351324901002741. Google Scholar
  38. 38.
    Mani, I., Maybury, M.T.: Advances in Automatic Text Summarization. MIT, Cambridge (1999)Google Scholar
  39. 39.
    Mann, W., Thompson, S.: Rhetorical structure theory: towards a functional theory of text organization. Text 8(3), 243–281 (1988)Google Scholar
  40. 40.
    Marcu, D.: From discourse structures to text summaries. In: The Proceedings of the ACL’97/EACL’97 Workshop on Intelligent Scalable Text Summarization, Madrid, pp. 82–88 (1997)Google Scholar
  41. 41.
    Maynard, D., Tablan, V., Cunningham, H., Ursu, C., Saggion, H., Bontcheva, K., Wilks, Y.: Architectural elements of language engineering robustness. J. Nat. Lang. Engin. Spec. Issue Robust Methods Anal. Nat. Lang. Data 8(2/3), 257–274 (2002)Google Scholar
  42. 42.
    Mihalcea, R.: Language independent extractive summarization. In: AAAI, Pittsburgh, Pennsylvania, pp. 1688–1689. Association for Computational Linguistics, Stroudsburg (2005)Google Scholar
  43. 43.
    Mihalcea, R., Tarau, P.: TextRank: Bringing order into texts. In: Proceedings of EMNLP-04and the 2004 Conference on Empirical Methods in Natural Language Processing, Barcelona (2004)Google Scholar
  44. 44.
    Nenkova, A., Passonneau, R., McKeown, K.: The pyramid method: incorporating human content selection variation in summarization evaluation. ACM Trans. Speech Lang. Process. 4(2), 1–23 (2007)Google Scholar
  45. 45.
    Hoa Trang Dang (ed.): NIST: Proceedings of the Text Analysis Conference. NIST, Gaithesburg (2008)Google Scholar
  46. 46.
    Okumura, M., Fukusima, T., Nanba, H., Hirao, T.: Text summarization challenge 2 text summarization evaluation at ntcir workshop 3. SIGIR Forum 38(1), 29–38 (2004)Google Scholar
  47. 47.
    Ono, K., Sumita, K., Miike, S.: Abstract generation based on rhetorical structure extraction. In: Proceedings of the International Conference on Computational Linguistics, Kyoto, Japan, pp. 344–348. ACL, Stroudsburg, USA (1994)Google Scholar
  48. 48.
    Over, P., Dang, H., Harman, D.: DUC in context. Inf. Process. Manag. 43, 1506–1520 (2007). DOI 10.1016/j.ipm.2007.01.019.
  49. 49.
    Owczarzak, K., Dang, H.: Overview of the tac 2010 summarization track. In: Proceedings of TAC 2010, NIST, Gaithersburg, MD, USA (2010)Google Scholar
  50. 50.
    Paice, C.D.: Constructing literature abstracts by computer: technics and prospects. Inf. Process. Manag. 26(1), 171–186 (1990)Google Scholar
  51. 51.
    Paice, C.D., Oakes, M.P.: A Concept-Based Method for Automatic Abstracting. Technical Report 27, Library and Information Commission, Wetherby (1999)Google Scholar
  52. 52.
    Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, ACL ’02, Philadelphia, pp. 311–318 (2002)Google Scholar
  53. 53.
    Radev, D., Allison, T., Blair-Goldensohn, S., Blitzer, J., Çelebi, A., Dimitrov, S., Drabek, E., Hakim, A., Lam, W., Liu, D., Otterbacher, J., Qi, H., Saggion, H., Teufel, S., Topper, M., Winkel, A., Zhang, Z.: MEAD — A platform for multidocument multilingual text summarization. In: Conference on Language Resources and Evaluation (LREC), Lisbon (2004)Google Scholar
  54. 54.
    Radev, D.R., Jing, H., Budzikowska, M.: Centroid-based summarization of multiple documents: sentence extraction, utility-based evaluation, and user studies. In: ANLP/NAACL Workshop on Summarization, Seattle (2000)Google Scholar
  55. 55.
    Radev, D.R., McKeown, K.R.: Generating natural language summaries from multiple on-line sources. Comput. Linguist. 24(3), 469–500 (1998)Google Scholar
  56. 56.
    Radev, D.R., Teufel, S., Saggion, H., Lam, W., Blitzer, J., Qi, H., Çelebi, A., Liu, D., Drabek, E.: Evaluation challenges in large-scale document summarization. In: Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Vol. 1, ACL ’03, Sapporo, Japan, pp. 375–382. ACL, Stroudsburg, USA (2003)Google Scholar
  57. 57.
    Saggion, H.: Multilingual multidocument summarization tools and evaluation. In: Proceedings of LREC 2006, Genoa, Italy. ELDA, Paris, France (2006)Google Scholar
  58. 58.
    Saggion, H.: Experiments on semantic-based clustering for cross-document coreference. In: Proceedings of the Third Joint International Conference on Natural Language Processing, AFNLP, Hyderabad, pp. 149–156 (2008)Google Scholar
  59. 59.
    Saggion, H.: SUMMA: a robust and adaptable summarization tool. Traitement Automatique des Langues 49(2), 103–125 (2008)Google Scholar
  60. 60.
    Saggion, H.: A classification algorithm for predicting the structure of summaries. In: UCNLG+Sum ’09: Proceedings of the 2009 Workshop on Language Generation and Summarisation, pp. 31–38. Association for Computational Linguistics, Morristown (2009)Google Scholar
  61. 61.
    Saggion, H.: Learning predicate insertion rules for document abstracting. In: CICLing, Tokyo, pp. 301–312. Springer, Berlin/New York (2011)Google Scholar
  62. 62.
    Saggion, H., Gaizauskas, R.: Multi-document summarization by cluster/profile relevance and redundancy removal. In: Proceedings of the Document Understanding Conference 2004, NIST, Boston (2004)Google Scholar
  63. 63.
    Saggion, H., Lapalme, G.: Generating indicative-informative summaries with sumUM. Comput. Linguist. 28, 497–526 (2002)Google Scholar
  64. 64.
    Saggion, H., Radev, D., Teufel, S., Lam, W.: Meta-evaluation of summaries in a cross-lingual environment using content-based metrics. In: Proceedings of COLING 2002, Taipei, pp. 849–855. Association for Computational Linguistics, Stroudsburg (2002)Google Scholar
  65. 65.
    Saggion, H., Radev, D., Teufel, S., Wai, L., Strassel, S.: Developing infrastructure for the evaluation of single and multi-document summarization systems in a cross-lingual environment. In: LREC 2002, Las Palmas, pp. 747–754 (2002)Google Scholar
  66. 66.
    Saggion, H., Teufel, S., Radev, D., Lam, W.: Meta-evaluation of summaries in a cross-lingual environment using content-based metrics. In: Proceedings of the 19th international conference on Computational linguistics - Vol. 1, COLING ’02, Taipei, pp. 1–7. Association for Computational Linguistics, Stroudsburg (2002)Google Scholar
  67. 67.
    Saggion, H., Torres-Moreno, J.M., da Cunha, I., SanJuan, E., Velazquez-Morales, P.: Multilingual summarization evaluation without human models. In: In Proceedings of COLING, Beijing (2010)Google Scholar
  68. 68.
    Salton, G., Allan, J., Singhal, A.: Automatic text decomposition and structuring. Inf. Process. Manag. 32(2), 127–138 (1996)Google Scholar
  69. 69.
    Sparck Jones, K.: What might be in a summary? In: K. Knorz, Womser-Hacker (eds.) Information Retrieval 93: Von der Modellierung zur Anwendung (1993)Google Scholar
  70. 70.
    Sparck Jones, K.: Automatic summarizing: factors and directions. In: Mani, I., Maybury, M. (eds.) Advances in Automatic Text Summarization. MIT, Cambridge (1999)Google Scholar
  71. 71.
    Sparck Jones, K., Endres-Niggemeyer, B.: Automatic summarizing. Inf. Process. Manag. 31(5), 625–630 (1995)Google Scholar
  72. 72.
    Spärck Jones, K., Galliers, J.R.: Evaluating Natural Language Processing Systems. Springer, Berlin (1996)Google Scholar
  73. 73.
    Swales, J.: Genre Analysis: English in Academic and Research Settings. Cambridge University Press, Cambridge (1990)Google Scholar
  74. 74.
    Teufel, S., Moens, M.: Argumentative classification of extracted sentences as a first step towards flexible abstracting. In: Mani, Maybury, M. (eds.) Advances in Automatic Text Summarization, pp. 155–171. MIT, Cambridge (1999)Google Scholar
  75. 75.
    Turner, J., Charniak, E.: Supervised and Unsupervised Learning for Sentence Compression. In: ACL, Michigan, Ann Arbor, USA. ACL, Stroudsburg, USA (2005)Google Scholar
  76. 76.
    Witbrock, M.J., Mittal, V.O.: Ultra-summarization: a statistical approach to generating highly condensed non-extractive summaries. In: In SIGIR99, Berkeley, pp. 315–316. ACM, New York (1999)Google Scholar
  77. 77.
    Zajic, D., Dorr, B., Lin, J., Schwartz, R.: Multi-candidate reduction: sentence compression as a tool for document summarization tasks. In: Information Processing and Management Special Issue on Summarization, p. 43. Elsevier, Amsterdam, The Netherlands (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.Department of Information and Communication TechnologiesUniversitat Pompeu FabraBarcelonaSpain
  2. 2.Laboratoire LaTTiCe-CNRSÉcole Normale Supérieure and Université Sorbonne-NouvelleMontrougeFrance

Personalised recommendations