Abstract
In this chapter we discuss the connection between anaphora/coreference resolution and summarization. The discussion follows the summarization framework based on Latent Semantic Analysis (LSA), however, the ideas can be applied to any sentence-scoring approach. After describing the ways of combining basic (lexical) features of the summarizer with those received from the coreference resolution system we try to answer the question whether coreference resolution helps to improve the quality of selected content even if coreference resolution systems are still far from perfect. Both single-document and multi-document summarization branches are discussed. Then we focus on post-processing techniques to improve the referential clarity and coherence of extracted summaries.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We rather use the term ‘coreference resolution’ as a more general term to anaphora resolution. However, when we discuss single-document summarization the term refers to the task of identifying successive mentions of the same discourse entity (intra-document coreference resolution/anaphora resolution), as opposed to the task of ‘inter-document coreference resolution’ appropriate in the case of multi-document summarization which involves collecting all information about an entity, including information expressed by appositions and other predicative constructions.
- 2.
The National Institute of Standards and Technology (NIST) initiated the Document Understanding Conference (DUC) series [11] to evaluate automatic text summarization. Its goal is to further progress in summarization and enable researchers to participate in large-scale experiments. Since 2008 DUC has moved to TAC (Text Analysis Conference) [52] that follows the summarization evaluation roadmap with new or upgraded tracks.
- 3.
When producing an update summary of a set of topic-related documents the summarizer assumes prior knowledge of the reader determined by a set of older documents of the same topic. The update summarizer thus must solve a novelty vs. redundancy problem.
- 4.
In the aspect summarization scenario a given list of core information aspects for different event types should be addressed in the automatic summaries.
- 5.
- 6.
The approach deals with object coreference and event coreference. They further consider the issue of referential relations beyond the identity relation covering a few domain-specific special cases.
- 7.
Available as open source software at http://guitar-essex.sourceforge.net/.
- 8.
This step includes heuristic methods for guessing agreement features.
- 9.
All system summaries were truncated to 100 words as traditionally done in DUC. ROUGE version and settings:
$$\displaystyle{\mathtt{ROUGEeval-1.4.2.pl-c95-m-n2-l100-s-24-aduc.xml.}}$$ - 10.
The previous sentence in the source is: “Walton continued talking with customers during the concert.”
- 11.
The multilingual named entity disambiguator and geo-tagger developed at the JRC have already been used for cross-lingual linking of multilingual news clusters produced by the EMM system [50].
- 12.
The use of the multilingual tools in higher-level applications can be seen at http://emm.newsexplorer.eu/.
References
Azzam, S., Humphreys, K., Gaizauskas, R.: Using coreference chains for text summarization. In: Proceedings of the ACL’99 Workshop on Conference and Its Applications, Baltimore. ACL (1999)
Baldwin, B., Morton, T.S.: Dynamic coreference-based summarization. In: Proceedings of EMNLP’98, Granada. ACL (1998)
Barzilay, R., Elhadad, M.: Using lexical chains for text summarization. In: Mani, I., Maybury, M. (eds.) Advances in Automated Text Summarization. MIT, Cambridge (1997)
Barzilay, R., Lapata, M.: Modeling local coherence: an entity-based approach. In: Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics, Ann Arbor. ACL (2005)
Belz, A., Kow, E., Viethen, J.: The GREC named entity generation challenge 2009: overview and evaluation results. In: Proceedings of ACL-IJCNLP’09 Workshop on Language Generation and Summarisation, Singapore. ACL (2009)
Bergler, S., Witte, R., Khalife, M., Li, Z., Rudzicz, F.: Using knowledge-poor coreference resolution for text summarization. In: Proceedings of DUC’03, Edmonton. NIST (2003)
Berry, M.W., Dumais, S.T., O’Brien, G.W.: Using linear algebra for intelligent IR. SIAM Rev. 37 (4), 573–595 (1995)
Boguraev, B., Kennedy, C.: Salience-based content characterisation of text documents. In: Mani, I., Maybury, M. (eds.) Advances in Automated Text Summarization. MIT, Cambridge (1997)
Charniak, E.: A maximum-entropy-inspired parser. In: Proceedings of NAACL’00, Philadelphia. ACL (2000)
Choi, F.Y.Y., Wiemer-Hastings, P., Moore, J.D.: Latent semantic analysis for text segmentation. In Proceedings of EMNLP, Pittsburgh. ACL (2001)
Document understanding conference: http://duc.nist.gov/
Edmundson, H.: New methods in automatic extracting. J. Assoc. Comput. Mach. 16 (2), 264–285 (1969). ACM
Giannakopoulos, G., El-Haj, M., Favre, B., Litvak, M., Steinberger, J., Varma, V.: TAC 2011 multiling pilot overview. In: Proceedings of the Text Analysis Conference 2011, Gaithersburg. NIST (2011)
Gong, Y., Liu, X.: Generic text summarization using relevance measure and latent semantic analysis. In: Proceedings of the 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, New Orleans, pp. 19–25. ACM (2001)
Grosz, B., Aravind, J., Scott, W.: Centering: a framework for modelling the local coherence of discourse. Comput. Linguist. 21 (2), 203–225. ACL (1995)
Hasler, L., Orasan, C., Mitkov, R.: Building better corpora for summarization. In: Proceedings of Corpus Linguistics, Lancaster. UCREL, Lancaster University (2003)
Hirschman, L.: MUC-7 coreference task definition, version 3.0. In: Proceedings of the 7th Message Understanding Conference, Fairfax. NIST (1998)
Hovy, E., Lin, C.: Automated text summarization in SUMMARIST. In: Mani, I., Maybury, M. (eds.) Advances in Automated Text Summarization. MIT, Cambridge (1997)
Kabadjov, M.: A comprehensive evaluation of anaphora resolution and discourse-new recognition. PhD thesis, University of Essex 2007
Kabadjov, M., Steinberger, J., Pouliquen, B., Steinberger, R., Poesio, M.: Multilingual statistical news summarisation: preliminary experiments with English. In: Proceedings of IAPWNC at the IEEE/WIC/ACM WI-IAT, Milano. IEEE Computer Society (2009)
Knott, A., Oberlander, J., O’Donnell, M., Mellish, C.: Beyond elaboration: the interaction of relations and focus in coherent text. In: Sanders, T., Schilperoord, J., Spooren, W. (eds.) Text Representation: Linguistic and Psycholinguistic Aspects. John Benjamins, Amsterdam/Philadelphia (2001)
Kupiec, J., Pedersen, J., Chen, F.: A trainable document summarizer. In: Proceedings of the 18th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Seattle, pp. 68–73. ACM (1995)
Landauer, C.T., Dumais, S.: A solution to plato’s problem: the latent semantic analysis theory of the acquisition, induction, and representation of knowledge. Psychol. Rev. 104, 211–240 (1997). American Psychological Association
Lin, C., Hovy, E.: Automatic evaluation of summaries using n-gram co-occurrence statistics. In: Proceedings of HLT-NAACL, Edmonton. ACL (2003)
Lin, C.: ROUGE: a package for automatic evaluation of summaries. In: Proceedings of the Workshop on Text Summarization Branches Out, Barcelona. ACL (2004)
Luhn, H.: The automatic creation of literature abstracts. IBM J. Res. Dev. 2 (2), 159–165 (1958). IBM
Mani, I. (ed.): Proceedings of the Workshop on Intelligent and Scalable Text Summarization at the Annual Joint Meeting of the ACL/EACL, Madrid. ACL (1997)
Mani, I., Firmin, T., House, D., Klein, G., Sundheim, B., Hirschman, L.: The TIPSTER summac text summarization evaluation. In: Proceedings of the 9th Meeting of the European Chapter of the Association for Computational Linguistics, Bergen. ACL (1999)
Mani, I., Maybury, M. (eds.): Advances in Automatic Text Summarization. MIT, Cambridge (1999)
Marcu, D.: From discourse structures to text summaries. In: Mani [27]
Maybury, M.: Generating summaries from event data. In: Mani and Maybury [29]
McKeown, K., Radev, D.: Generating summaries of multiple news articles. In: Proceedings of the 18th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Seattle, pp. 74–82. ACM (1995)
Morris, A., Kasper, G., Adams, D.: The effects and limitations of automatic text condensing on reading comprehension performance. Inf. Syst. Res. 3 (1), 17–35 (1992). INFORMS
Mueller, C., Strube, M.: MMAX: a tool for the annotation of multi-modal corpora. In: Proceedings of the 2nd IJCAI Workshop on Knowledge and Reasoning in Practical Dialogue Systems, Seattle. Morgan Kaufmann (2001)
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). ACM
Orasan, C., Mitkov, R., Hasler, L.: CAST: a computer-aided summarization tool. In: Proceedings of EACL’03, Budapest. ACL (2003)
Over, P., Dang, H., Harman, D.: DUC in context. Inf. Process. Manag. 43 (6), 1506–1520 (2007). Special Issue on Text Summarisation (Donna Harman, ed.). Elsevier.
Pitler, E., Louis, A., Nenkova, A.: Automatic evaluation of linguistic quality in multi-document summarization. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, Uppsala, pp 544–554. ACL (2010)
Poesio, M., Kabadjov, M.: A general-purpose, off-the-shelf anaphora resolution module: implementation and preliminary evaluation. In: Proceedings of LREC, Lisbon. ELRA (2004)
Poesio, M., Stevenson, R., Di Eugenio, B., Hitzeman, J.: Centering: a parametric theory and its instantiations. Comput. Linguist. 30 (3), 309–363 (2004). ACL
Pouliquen, B., Kimler, M., Steinberger, R., Ignat, C., Oellinger, T., Blackler, K., Fuart, F., Zaghouani, W., Widiger, A., Forslund, A., Best, C.: Geocoding multilingual texts: recognition, disambiguation and visualisation. In: Proceedings of the 5th LREC, Genoa, pp. 53–58. ELRA (2006)
Pouliquen, B., Steinberger, R.: Automatic construction of multilingual name dictionaries. In: Goutte, C., Cancedda, N., Dymetman, M., Foster, G. (eds.) Learning Machine Translation. MIT, Cambridge (2009)
Radev, D., Jing, H., Budzikowska, M.: Centroid-based summarization of multiple documents. In: ANLP/NAACL Workshop on Automatic Summarization, Seattle. ACL (2000)
Radev, D., Teufel, S., Saggion, H., Lam, W., Blitzer, J., Qi, H., Celebi, A., Liu, D., Drabek, E.: Evaluation challenges in large-scale document summarization. In: Proceeding of the 41st meeting of the Association for Computational Linguistics, Sapporo. ACL (2003)
Sparck-Jones, K.: Automatic summarising: factors and directions. In: Mani and Maybury [29]
Steinberger, J., Ježek, K.: Text summarization and singular value decomposition. Lect. Notes Comput. Sci. 2457, 245–254 (2004). Springer
Steinberger, J., Kabadjov, M., Poesio, M.: Improving LSA-based summarization with anaphora resolution. In: Proceedings of HLT/EMNLP’05, Vancouver, pp. 1–8. ACL (2005)
Steinberger, J., Kabadjov, M., Pouliquen, B., Steinberger, R., Poesio, M.: WB-JRC-UT’s participation in TAC 2009: update summarization and AESOP tasks. In: Proceedings of TAC’09, Gaithersburg. NIST (2009)
Steinberger, J., Poesio, M., Kabadjov, M., Ježek, K.: Two uses of anaphora resolution in summarization. Inf. Process. Manag. 43 (6), 1663–1680 (2007). Elsevier
Steinberger, R., Pouliquen, B., Ignat, C.: Using language-independent rules to achieve high multilinguality in text mining. In: Fogelman-Soulié, F., Perrotta, D., Piskorski, J., Steinberger, R. (eds.) Mining Massive Data Sets for Security. IOS-Press, Amsterdam (2009)
Stuckardt, R.: Coreference-based summarization and question answering: a case for high precision anaphor resolution. In: International Symposium on Reference Resolution and Its Applications to Question Answering and Summarization, Venice (2003)
Text analysis conference: http://www.nist.gov/tac
Turchi, M., Steinberger, J., Kabadjov, M., Steinberger, R.: Using parallel corpora for multilingual (multi-document) summarisation evaluation. In: Proceedings of CLEF-10, pp. 52–63. Springer (2010)
Wan, X., Li, H., Xiao, J.: Cross-language document summarization based on machine translation quality prediction. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pp. 917–926. ACL (2010)
Acknowledgements
This work was supported by project “NTIS - New Technologies for Information Society”, European Centre of Excellence, CZ.1.05/1.1.00/02.0090, and by project MediaGist, EU’s FP7 People Programme (Marie Curie Actions), no. 630786.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Steinberger, J., Kabadjov, M., Poesio, M. (2016). Coreference Applications to Summarization. In: Poesio, M., Stuckardt, R., Versley, Y. (eds) Anaphora Resolution. Theory and Applications of Natural Language Processing. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-47909-4_15
Download citation
DOI: https://doi.org/10.1007/978-3-662-47909-4_15
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-47908-7
Online ISBN: 978-3-662-47909-4
eBook Packages: Computer ScienceComputer Science (R0)