Advertisement

Full Paraphrase Generation for Fragments in Dialogue

  • Christian Ebert
  • Shalom Lappin
  • Howard Gregory
  • Nicolas Nicolov
Part of the Text, Speech and Language Technology book series (TLTB, volume 22)

Abstract

Much previous work on generation has focused on the general problem of producing lexical strings from abstract semantic representations. We consider generation in the context of a particular task, creating full sentential paraphrases of fragments in dialogue. When the syntactic, semantic and phonological information provided by a dialogue fragment resolution system is made accessible to a generation component, much of the indeterminacy of lexical selection is eliminated.

Keywords

Personnel Manager Polar Question Personnel Department Antecedent Clause Head Drive Phrase Structure Grammar 
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. Becker, T. and Busemann, S., editors (1999). May I Speak Freely? Between Templates and Free Choice in Natural Language Generation. Workshop at the 23rd German Annual Conference for Artificial Intelligence (KI’ 99), Saarbrucken. DFKI.Google Scholar
  2. Cooper, R., Larsson, S., Poesio, M., Traum, D., and Matheson, C. (1999). Coding instructional dialogue for information states. In Task Oriented Instructional Dialogue (TRINDI): Deliverable 1.1. University of Gothenburg, Gothenburg.Google Scholar
  3. Erbach, G. (1996). ProFIT: Prolog with features, inheritance and templates. In Proceedings of the 7th European Conference of the Association for Computational Linguistics, pages 180–187.Google Scholar
  4. Ginzburg, J. (2001). Clarification ellipsis and nominal anaphora. In Bunt, H., editor, Computing meaning, volume 2. Kluwer, Dordrecht.Google Scholar
  5. Ginzburg, J., Gregory, H., and Lappin, S. (2001). SHARDS: Fragment resolution in dialogue. In Bunt, H., van der Sluis, I., and Thijse, E., editors, Proceedings of the 4th International Workshop on Computational Semantics (IWCS-4), pages 156–172, Tilburg.Google Scholar
  6. Ginzburg, J. and Sag, I. (2000). English Interrogative Constructions. Studies in Constraint-based Lexicalism. CSLI Publications, Stanford, California.Google Scholar
  7. Gregory, H. and Lappin, S. (1999). Antecedent contained ellipsis in HPSG. In Webelhuth, G., Koenig, J. P., and Kathol, A., editors, Lexical and Constructional Aspects of Linguistic Explanation, pages 331–356. CSLI Publications, Stanford.Google Scholar
  8. Kay, M. (1996). Chart generation. In Proceedings of the 34th Annual Meeting of the ACL, pages 200–204.Google Scholar
  9. McKeown, K. R. (1985). Text Generation: Using Discourse Strategies and Focus Constraints to Generate Natural Language Text. Cambridge University Press, Cambridge.CrossRefGoogle Scholar
  10. Nicolov, N. and Mellish, C. (2000). PROTECTOR: Efficient Generation with Lexicalized Grammars. In Recent Advances in Natural Language Processing, Current Issues in Linguistic Theory (CILT 189), pages 221–243. John Benjamins, Amsterdam & Philadelphia.Google Scholar
  11. Pollard, C. and Sag, I. (1994). Head Driven Phrase Structure Grammar. University of Chicago Press and CSLI Publications, Chicago.Google Scholar
  12. Purver, M. (2001). Adding a realistic lexicon to SHARDS. Technical report, Department of Computer Science, King’s College London.Google Scholar
  13. Reiter, E. (1995). NLG vs. templates. In Proceedings of the Fifth European Workshop on Natural-Language Generation (ENLGW-1995), Leiden, The Netherlands.Google Scholar
  14. Sag, I. (1997). English relative clause constructions. Journal of Linguistics, 33:431–184.CrossRefGoogle Scholar
  15. Shieber, S., Pereira, F., van Noord, G., and Moore, R. (1990). Semantic-head-driven generation. Computational Linguistics, 16:30–42.Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2003

Authors and Affiliations

  • Christian Ebert
    • 1
  • Shalom Lappin
    • 1
  • Howard Gregory
    • 1
  • Nicolas Nicolov
    • 2
  1. 1.Department of Computer ScienceKing’s College LondonLondonUK
  2. 2.IBM T. J. Watson Research CenterYorktownUSA

Personalised recommendations