Exploiting Lexical Conceptual Structure for Paraphrase Generation

  • Atsushi Fujita
  • Kentaro Inui
  • Yuji Matsumoto
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3651)

Abstract

Lexical Conceptual Structure (LCS) represents verbs as semantic structures with a limited number of semantic predicates. This paper attempts to exploit how LCS can be used to explain the regularities underlying lexical and syntactic paraphrases, such as verb alternation, compound word decomposition, and lexical derivation. We propose a paraphrase generation model which transforms LCSs of verbs, and then conduct an empirical experiment taking the paraphrasing of Japanese light-verb constructions as an example. Experimental results justify that syntactic and semantic properties of verbs encoded in LCS are useful to semantically constrain the syntactic transformation in paraphrase generation.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Baker, C.F., Fillmore, C.J., Lowe, J.B.: The Berkeley FrameNet project. In: Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and the 17th International Conference on Computational Linguistics COLING-ACL, pp. 86–90 (1998)Google Scholar
  2. 2.
    Carreras, X., Màrques, L.: Introduction to the CoNLL-2004 shared task: semantic role labeling. In: Proceedings of 8th Conference on Natural Language Learning CoNLL, pp. 89–97 (2004)Google Scholar
  3. 3.
    Dorr, B.J.: Large-scale dictionary construction for foreign language tutoring and interlingual machine translation. Machine Translation 12(4), 271–322 (1997)CrossRefGoogle Scholar
  4. 4.
    Dras, M.: Tree adjoining grammar and the reluctant paraphrasing of text. Ph.D. thesis, Division of Information and Communication Science, Macquarie University (1999)Google Scholar
  5. 5.
    Fujita, A., Inui, K., Matsumoto, Y.: Detection of incorrect case assignments in automatically generated paraphrases of Japanese sentences. In: Proceedings of the 1st International Joint Conference on Natural Language Processing IJCNLP, pp. 14–21 (2004)Google Scholar
  6. 6.
    Gildea, D., Jurafsky, D.: Automatic labeling of semantic roles. Computational Linguistics 28(3), 245–288 (2002)CrossRefGoogle Scholar
  7. 7.
    Iordanskaja, L., Kittredge, R., Polguère, A.: Lexical selection and paraphrase in a meaning-text generation model. In: Paris, C.L., Swartout, W.R., Mann, W.C. (eds.) Natural Language Generation in Artificial Intelligence and Computational Linguistics, pp. 293–312. Kluwer Academic Publishers, Dordrecht (1991)Google Scholar
  8. 8.
    Jackendoff, R.: Semantic structures. The MIT Press, Cambridge (1990)Google Scholar
  9. 9.
    Kageyama, T.: Verb semantics. Kurosio Publishers (1996) (in Japanese)Google Scholar
  10. 10.
    Kaji, N., Kurohashi, S.: Recognition and paraphrasing of periphrastic and overlapping verb phrases. In: Proceedings of the 4th International Conference on Language Resources and Evaluation LREC Workshop on Methodologies and Evaluation of Multiword Units in Real-world Application (2004)Google Scholar
  11. 11.
    Kondo, K., Sato, S., Okumura, M.: Paraphrasing by case alternation. IPSJ Journal 42(3), 465–477 (2001) (in Japanese)Google Scholar
  12. 12.
    Levin, B.: English verb classes and alternations: a preliminary investigation. Chicago Press (1993)Google Scholar
  13. 13.
    Mel’čuk, I., Polguère, A.: A formal lexicon in meaning-text theory (or how to do lexica with words). Computational Linguistics 13(3-4), 261–275 (1987)Google Scholar
  14. 14.
    Muraki, S.: Various aspects of Japanese verbs. Hitsuji Syobo (1991) (in Japanese)Google Scholar
  15. 15.
    Oishi, A., Matsumoto, Y.: Detecting the organization of semantic subclasses of Japanese verbs. International Journal of Corpus Linguistics 2(1), 65–89 (1997)CrossRefGoogle Scholar
  16. 16.
    Palmer, M., Gildea, D., Kingsbury, P.: The Proposition Bank: an annotated corpus of semantic roles. Computational Linguistics 31(1), 71–106 (2005)CrossRefGoogle Scholar
  17. 17.
    Pustejovsky, J.: The generative lexicon. The MIT Press, Cambridge (1995)Google Scholar
  18. 18.
    Sato, S.: Automatic paraphrase of technical papers’ titles. IPSJ Journal 40(7), 2937–2945 (1999) (in Japanese)Google Scholar
  19. 19.
    Takeuchi, K., Kageura, K., Koyama, T.: An LCS-based approach for analyzing Japanese compound nouns with deverbal heads. In: Proceedings of the 2nd International Workshop on Computational Terminology CompuTerm, pp. 64–70 (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Atsushi Fujita
    • 1
  • Kentaro Inui
    • 2
  • Yuji Matsumoto
    • 2
  1. 1.Graduate School of InformaticsKyoto University 
  2. 2.Graduate School of Information ScienceNara Institute of Science and Technology 

Personalised recommendations