An Adjacency Model for Sentence Ordering in Multi-document Summarization

  • Yu Nie
  • Donghong Ji
  • Lingpeng Yang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4182)


In this paper, we proposed a new method named adjacency based ordering to order sentences for summarization tasks. Given a group of sentences to be organized into the summary, connectivity of each pair of sentences is learned from source documents. Then a top-first strategy is implemented to define the sentence ordering. It provides a solution of ordering texts while other information except the source documents is not available. We compared this method with other existing sentence ordering methods. Experiments and evaluations are made on data collection of DUC04. The results show that this method distinctly outperforms other existing sentence ordering methods. Its low input requirement also makes it capable to most summarization and text generation tasks.


Source Document Automatic Evaluation Feature Pair Sentence Pair Output Ordering 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Barzilay, R., Elhadad, N., McKeown, K.R.: Sentence ordering in multidocument summarization. In: Proceedings of the First International Conference on Human Language Technology Research (HLT 2001), San Diego, CA, pp. 149–156 (2001)Google Scholar
  2. 2.
    Barzilay, R., Elhadad, N., McKeown, K.R.: Inferring strategies for sentence ordering in multidocument news summarization. Journal of Artificial Intelligence Research 17, 35–55 (2002)MATHGoogle Scholar
  3. 3.
    Blair-Goldensohn, S., Evans, D.: Columbia University at DUC 2004. In: Proceedings of the 4th Document Understanding Conference (DUC 2004) (May 2004)Google Scholar
  4. 4.
    Bollegala, D., Okazaki, N., Ishizuka, M.: A machine learning approach to sentence ordering for multidocument summarization and it’s evaluation. In: Dale, R., Wong, K.-F., Su, J., Kwong, O.Y. (eds.) IJCNLP 2005. LNCS (LNAI), vol. 3651, pp. 624–635. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  5. 5.
    Boros, E., Kantor, P.B., Neu, D.J.: A Clustering Based Approach to Creating Multi-Document Summaries. In: DUC 2001 workshop (2001)Google Scholar
  6. 6.
    Dubes, R.C., Jain, A.K.: Algorithms for Clustering Data. Prentice Hall, Englewood Cliffs (1988)MATHGoogle Scholar
  7. 7.
    Hardy, H., Shimizu, N.: Cross-Document Summarization by Concept Classification. In: SIGIR 2002, pp. 121–128 (2002)Google Scholar
  8. 8.
    Lapata, M.: Probabilistic text structuring: Experiments with sentence ordering. In: Proceedings of the annual meeting of ACL, pp. 545–552 (2003)Google Scholar
  9. 9.
    Lebanon, G., Lafferty, J.: Combining rankings using conditional probability models on permutations. In: Sammut, C., Hoffmann, A. (eds.) Proceedings of the 19th International Conference on Machine Learning. Morgan Kaufmann Publishers, San Francisco (2002)Google Scholar
  10. 10.
    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., Zhu, Z.: MEAD - a platform for multidocument multilingual text summarization. In: Proceedings of LREC 2004, Lisbon, Portugal (May 2004)Google Scholar
  11. 11.
    Siddharthan, A., Nenkova, A., McKeown, K.: Syntactic Simplication for Improving Content Selection in Multi-Document Summarization. In: Proceeding of COLING 2004, Geneva, Switzerland (2004)Google Scholar
  12. 12.
    Stein, G.C., Bagga, A., Wise, G.B.: Multi-Document Summarization: Methodologies and Evaluations. In: Conference TALN 2000, Lausanne, October 16-18 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Yu Nie
    • 1
  • Donghong Ji
    • 1
  • Lingpeng Yang
    • 1
  1. 1.Institute for Infocomm ResearchSingapore

Personalised recommendations