In this paper we present a first-ever manually-built Chinese sentence compression corpus. Based on this corpus, we develop a Chinese sentence compression system and study various measures for evaluation of Chinese sentence compression. We find that 1) using multi-references is very helpful for automatic evaluation in Chinese sentence compression; and 2) besides relational F1, some machine translation evaluation measures are correlated well with human judgments and thus are very promising for future use in this task.


sentence compression Chinese corpus system evaluation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bikel, D.M.: Intricacies of Collins’ Parsing Model. Computational Linguistics 30(4), 479–511 (2004)CrossRefzbMATHGoogle Scholar
  2. 2.
    Clarke, J., Lapata, M.: Global inference for sentence compression: An integer linear programming approach. Journal of Artificial Intelligence Research 1(31), 399–429 (2008)Google Scholar
  3. 3.
    Clarke, J., Lapata, M.: Models for sentence compression: A comparison across domains, training requirements and evaluation measures. In: Proceedings of ACL-COLING, pp. 377–384 (2006b)Google Scholar
  4. 4.
    Cohn, T., Lapata, M.: Sentence compression beyond word deletion. In: Proceedings of the 22nd COLING, pp. 137–144 (2009)Google Scholar
  5. 5.
    Doddington, G.: Automatic evaluation of machine translation quality using n-gram co-occurrence statistics. In: Proceeding of HLT 2002 Proceedings of the Second International Conference on Human Language Technology Research, pp. 138–145 (2002)Google Scholar
  6. 6.
    Fleiss, J.L.: Measuring nominal scale agreement among many raters. Psychological Bulletin 76(5), 378–382 (1971)CrossRefGoogle Scholar
  7. 7.
    Galley, M., McKeown, K.R.: Lexicalized Markov Grammars for Sentence Compression. In: Proceedings of HLT-NAACL, pp. 180–187 (2007)Google Scholar
  8. 8.
    Jing, H.: Sentence Reduction for automatic summarization. In: Proceedings of ANLP, pp. 310–315 (2000)Google Scholar
  9. 9.
    Knight, K., Marcu, D.: Statistical-based summarization-step one: sentence compression. In: Proceedings of AAAI 2000, pp. 703–710 (2000)Google Scholar
  10. 10.
    Knight, K., Marcu, D.: Summarization beyond sentence extraction: a probabilistic approach to sentence compression. Artificial Intelligence 139(1), 91–107 (2002)MathSciNetCrossRefzbMATHGoogle Scholar
  11. 11.
    McDonald, R.: Discriminative sentence compression with soft syntactic constraints. In: Proceedings of EACL, pp. 297–304 (2006)Google Scholar
  12. 12.
    Nießen, S., Och, F.J., Leusch, G., Ney, H.: An evaluation tool for machine translation: Fast evaluation for machine translation research. In: Proceedings of the Second International Conference on Language Resources and Evaluation (LREC), pp. 39–45 (2000)Google Scholar
  13. 13.
    Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a Method for Automatic Evaluation of Machine Translation. In: Proceedings of 40th Annual Meeting of ACL, pp. 311–318 (2002)Google Scholar
  14. 14.
    Riezler, S., King, T.H., Crouch, R., Zaenen, A.: Statistical sentence condensation using ambiguity packing and stochastic disambiguation methods for lexical-functional grammar. In: Proceedings of HLT-NAACL, pp. 118–125 (2003)Google Scholar
  15. 15.
    Snover, M., Dorr, B., Schwartz, R., Micciulla, L., Makhoul, J.: A Study of Translation Edit Rate with Targeted Human Annotation. In: Proceedings of Association for Machine Translation in the Americas, pp. 223–231 (2006)Google Scholar
  16. 16.
    Tillmann, C., Vogel, S., Ney, H., Zubiaga, A., Sawaf, H.: Accelerated DP based search for statistical translation. In: Proceedings of European Conference on Speech Communication and Technology, pp. 2667–2670 (1997)Google Scholar
  17. 17.
    Turian, J.P., Shen, L., Melamed, I.D.: Evaluation of Machine Translation and its Evaluation. In: Proceedings of MT Summit IX, pp. 386–393 (2003)Google Scholar
  18. 18.
    Turner, J.P., Charniak, E.: Supervised and unsupervised learning for sentence compression. In: Proceedings of 43rd Annual Meeting of ACL, pp. 290–297 (2005)Google Scholar
  19. 19.
    Xue, N., Xia, F., Chiou, F., Palmer, M.: The Penn Chinese TreeBank: Phrase structure annotation of a large corpus. Natural Language Engineering 11(2), 207–238 (2005)CrossRefGoogle Scholar
  20. 20.
    Yamangil, E., Nelken, R.: Mining Wikipedia revision histories for improving sentence compression. In: Proceedings of 46th Annual Meeting of ACL, pp. 137–140 (2008)Google Scholar
  21. 21.
    Yamangil, E., Shieber, S.M.: Bayesian synchronous tree-substitution grammar induction and its application to sentence compression. In: Proceedings of 48th Annual Meeting of ACL, pp. 934–947 (2010)Google Scholar
  22. 22.
    Yoshikawa, K., Iida, R., Hirao, T., Okumura, M.: Sentence Compression with Semantic Role Constraints. In: Proceedings of 50th Annual Meeting of ACL, pp. 349–353 (2012)Google Scholar
  23. 23.
    Zhang, Y., Clark, S.: Syntactic Processing Using the Generalized Perceptron and Beam Search. Computational Linguistics 37(1), 105–151 (2011)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Chunliang Zhang
    • 1
  • Minghan Hu
    • 1
  • Tong Xiao
    • 1
  • Xue Jiang
    • 1
  • Lixin Shi
    • 1
  • Jingbo Zhu
    • 1
  1. 1.Natural Language LabNortheastern UniversityShenyangChina

Personalised recommendations