Sentence Compression by Removing Recursive Structure from Parse Tree

  • Seiji Egawa
  • Yoshihide Kato
  • Shigeki Matsubara
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5351)


Sentence compression is a task of generating a grammatical short sentence from an original sentence, retaining the most important information. The existing methods of removing the constituents in the parse tree of an original sentence cannot deal with recursive structures which appear in the parse tree. This paper proposes a method to remove such structure and generate a grammatical short sentence. Compression experiments have shown the method to provide an ability to sentence compression comparable to the existing methods and generate good compressed sentences for sentences including recursive structures, which the previous methods failed to compress.


sentence compression text summarization phrase structure recursive structure maximum entropy method 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Berger, A.L., Della Pietra, V.J., Della Pietra, S.A.: A Maximum Entropy Approach to Natural Language Processing. Computational Linguistics 22(1), 39–71 (1996)Google Scholar
  2. 2.
    Knight, K., Marcu, D.: Statistics-Based Summarization – Step One: Sentence Compression. In: AAAI/IAAI 2000, pp. 703–710. MIT Press, Cambridge (2000)Google Scholar
  3. 3.
    Knight, K., Marcu, D.: Summarization beyond Sentence Extraction: A Probabilistic Approach to Sentence Compression. Artificial Intelligence 139, 91–107 (2002)CrossRefzbMATHGoogle Scholar
  4. 4.
    Mani, I.: Automatic Summarization. John Benjamins, Philadelphia (2001)CrossRefzbMATHGoogle Scholar
  5. 5.
    Nguyen, M.L., Horiguchi, S., Shimazu, A., Ho, T.B.: Example-Based Sentence Reduction Using the Hidden Markov Model. ACM Trans. on Asian Language Information Processing 3(2), 146–158 (2004)CrossRefGoogle Scholar
  6. 6.
    Papineni, K., Roukos, S., Word, T., Zhu, W.J.: BLEU: A Method for Automatic Evaluation of Machine Translation. In: ACL 2001, pp. 311–318. ACL, Morristown (2001)Google Scholar
  7. 7.
    Turner, J., Charniak, E.: Supervised and Unsupervised Learning for Sentence Compression. In: ACL 2005, pp. 290–297. ACL, Morristown (2005)Google Scholar
  8. 8.
    Unno, Y., Ninomiya, T., Miyao, Y., Tsujii, J.: Trimming CFG Parse Trees for Sentence Compression Using Machine Learning Approaches. In: COLING/ACL 2006, pp. 850–857. ACL, Morristown (2006)Google Scholar
  9. 9.
    Vandeghinste, V., Pan, Y.: Sentence Compression for Automated Subtitling: A Hybrid Approach. In: ACL 2004 Workshop on Text Summarization, pp. 89–95. ACL, Morristown (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Seiji Egawa
    • 1
  • Yoshihide Kato
    • 2
  • Shigeki Matsubara
    • 3
  1. 1.Graduate School of Information ScienceNagoya UniversityJapan
  2. 2.Graduate School of International DevelopmentNagoya UniversityJapan
  3. 3.Information Technology CenterNagoya UniversityNagoyaJapan

Personalised recommendations