Advertisement

SEGUE: A Hybrid Case-Based Surface Natural Language Generator

  • Shimei Pan
  • James Shaw
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3123)

Abstract

This paper presents Segue, a hybrid surface natural language generator that employs case-based paradigm but performs rule-based adaptations. It uses an annotated corpus as its knowledge source and employs grammatical rules to construct new sentences. By using adaptation-guided retrieval to select cases that can be adapted easily to the desired output, Segue simplifies the process and avoids generating ungrammatical sentences. The evaluation results show the system generates grammatically correct sentences (91%), but disfluency is still an issue.

Keywords

Machine Translation Retrieval Phase Insertion Operator Annotate Corpus Grammatical Rule 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Kolodner, J.: Case-Based Reasoning. Morgan Kaufmann, San Francisco (1993)Google Scholar
  2. 2.
    Aamodt, A., Plaza, E.: Case-based reasoning; foundational issues, methodological variations, and system approaches. AI Communications 7 (1994)Google Scholar
  3. 3.
    Lankilde, I., Knight, K.: Generation that exploits corpus-based statiscal knowledge. In: Proc. of the COLING and the ACL, Montreal, Canada (1998)Google Scholar
  4. 4.
    Bangalore, S., Rambow, O.: Exploiting a probabilistic hierarchical model for generation. In: Proc. of the COLING (2000)Google Scholar
  5. 5.
    Ratnaparkhi, A.: Trainable methods for surface natural language generation. In: Proc. of the NAACL, Seattle, WA (2000)Google Scholar
  6. 6.
    Chai, J., Pan, S., Zhou, M., Houck, K.: Context-based multimodal understandin gin conversational systems. In: Proc. of International Conference on Multimodal Interfaces (2002) Google Scholar
  7. 7.
    Pan, S., Weng, W.: Designing a speech corpus for instance-based spoken language generation. In: Proc. of INLG, New York (2002) Google Scholar
  8. 8.
    Somers, H.: EBMT seen as case-based reasoning. In: MT Summit VIII Workshop on Example-Based Machine Translation, Santiago de Compostela, Spain (2001) Google Scholar
  9. 9.
    Brown, R.D.: Adding linguistic knowledge to a lexical example-based translation system. In: Proc. of the International Conference on Theoretical and Methodological Issues in Machine Translation, Chester, UK (1999) Google Scholar
  10. 10.
    Ristad, E.S., Yianilos, P.N.: Learning string edit distance. IEEE Transactions on Pattern Analysis and Machine Intelligence 20 (1998)Google Scholar
  11. 11.
    Smyth, B., Keane, M.T.: Experiements on adaptation-guided retrieval in case based design. In: Proc. of the ICCBR (1995) Google Scholar
  12. 12.
    Leake, D.B.: Adaptive similarity assessment for case-based explanation. International Journal of Expert Systems 8 (1995)Google Scholar
  13. 13.
    Robin, J., McKeown, K.R.: Corpus analysis for revision-based generation of complex sentences. In: Proc. of AAAI, Washington, DC (1993) Google Scholar
  14. 14.
    Shaw, J.: Clause aggregation using linguistic knowledge. In: Proc. of the IWNLG (1998) Google Scholar
  15. 15.
    Walker, M., Rambow, O., Rogati, M.: SPot: A trainable sentence planner. In: Proc. of the NAACL (2001) Google Scholar
  16. 16.
    Varges, S., Mellish, C.: Instance-based natural language generation. In: Proc. of the NAACL, Pittsburgh, PA (2001) Google Scholar
  17. 17.
    Oberlander, J., Brew, C.: Stochaastic text generation. Philosophical Transactions of the Royal Society 358 (2000)Google Scholar
  18. 18.
    Collins, B., Cuningham, P.: Adaptation-guided retrieval in EBMT: A case-based approach to machine translation. In: Proc. of EWCBR (1996) Google Scholar
  19. 19.
    Somers, H.: Example-based machine translation. Machine Translation 14 (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Shimei Pan
    • 1
  • James Shaw
    • 1
  1. 1.IBM T.J. Watson Research CenterHawthorneUSA

Personalised recommendations