Skip to main content
SpringerLink
Log in

Learning grammatical structure using statistical decision-trees

  • Invited Talks
  • Conference paper
  • First Online:
Grammatical Interference: Learning Syntax from Sentences (ICGI 1996)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 1147))

Included in the following conference series:

Abstract

In this paper, I describe SPATTER, a statistical parser based on decision-tree learning techniques which avoids the difficulties of grammar development simply by having no grammar. Instead, the parser is driven by statistical pattern recognizers, in the form of decision trees, trained on correctly parsed sentences. This approach to grammatical inference results in a parser which constructs a complete parse for every sentence and achieves accuracy rates far better than any previously published result.

This paper discusses work performed at the IBM Speech Recognition Group under Frederick Jelinek and at the BBN Speech Recognition Group under John Makhoul.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. L. R. Bahl, P. F. Brown, P. V. deSouza, and R. L. Mercer. 1989. A tree-based statistical language model for natural language speech recognition. IEEE Transactions on Acoustics, Speech, and Signal Processing, Vol. 36, No. 7, pages 1001–1008.

    Google Scholar 

  2. J. K. Baker. 1975. Stochastic modeling for automatic speech understanding. Speech Recognition, pages 521–542.

    Google Scholar 

  3. L. E. Baum. 1972. An inequality and associated maximization technique in statistical estimation of probabilistic functions of markov processes. Inequalities, Vol. 3, pages 1–8.

    Google Scholar 

  4. E. Black and et al. 1991. A procedure for quantitatively comparing the syntactic coverage of english grammars. Proceedings of the February 1991 DARPA Speech and Natural Language Workshop, pages 306–311.

    Google Scholar 

  5. E. Black, R. Garside, and G. Leech. 1993. Statistically-driven computer grammars of english: the ibm/lancaster approach. Rodopi, Atlanta, Georgia.

    Google Scholar 

  6. E. Black, J. Lafferty, and S. Roukos. 1992. Development and evaluation of a broadcoverage probabilistic grammar of english-language computer manuals. Proceedings of the Association for Computational Linguistics, 1992.

    Google Scholar 

  7. L. Breiman, J. H. Friedman, R. A. Olshen, and C. J. Stone. 1984. Classification and Regression Trees. Wadsworth and Brooks, Pacific Grove, California.

    Google Scholar 

  8. P. F. Brown, V. Della Pietra, P. V. deSouza, J. C. Lai, and R. L. Mercer. 1992. “Class-based n-gram models of natural language.” Computational Linguistics, 18(4), pages 467–479.

    Google Scholar 

  9. G. Carroll and E. Charniak 1992. Learning probabilistic dependency grammars from labeled text. Working Notes, Fall Symposium Series, AAAI, pages 25–32.

    Google Scholar 

  10. F. Jelinek, J. Lafferty, D. M. Magerman, R. Mercer, A. Ratnaparkhi, and S. Roukos. 1994. Decision tree parsing using a hidden derivation model. Proceedings of the 1994 Human Language Technology Workshop, pages 272–277.

    Google Scholar 

  11. F. Jelinek, J. D. Lafferty, and R. L. Mercer. 1992. Basic methods of probabilistic context-free grammars. Speech Recognition and Understanding: Recent Advances, Trends, and Applications. Proceedings of the NATO Advanced Study Institute, pages 345–360.

    Google Scholar 

  12. J. Kupiec. 1991. A trellis-based algorithm for estimating the parameters of a hidden stochastic context-free grammar. Proceedings of the February 1991 DARPA Speech and Natural Language Workshop, pages 241–246, 1991.

    Google Scholar 

  13. D. M. Magerman. 1994. Natural Language Parsing as Statistical Pattern Recognition. Doctoral dissertation. Stanford University, Stanford, California.

    Google Scholar 

  14. D. M. Magerman. 1995. Statistical decision-tree models for parsing. Proceedings of the Association for Computational Linguistics, 1995.

    Google Scholar 

  15. D. M. Magerman and M. P. Marcus. 1990. Parsing a natural language using mutual information statistics. Proceedings of AAAI-90.

    Google Scholar 

  16. F. Pereira and Y. Schabes. 1992. Inside-outside reestimation from partially bracketed corpora. Proceedings of the February 1992 DARPA Speech and Natural Language Workshop, pages 122–127.

    Google Scholar 

  17. V. Pratt. 1973. A linguistics oriented programming language. Proceedings of the Third International Joint Conference on Artificial Intelligence.

    Google Scholar 

  18. Y. Schabes and R. Waters. 1993. Stochastic lexicalized context-free grammar. Proceedings of the August 1993 International Workshop on Parsing Technologies.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Renaissance Technologies Corp., USA

    David M. Magerman

Authors
  1. David M. Magerman
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Laurent Miclet Colin de la Higuera

Rights and permissions

Reprints and permissions

Copyright information

© 1996 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Magerman, D.M. (1996). Learning grammatical structure using statistical decision-trees. In: Miclet, L., de la Higuera, C. (eds) Grammatical Interference: Learning Syntax from Sentences. ICGI 1996. Lecture Notes in Computer Science, vol 1147. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0033339

Download citation

  • DOI: https://doi.org/10.1007/BFb0033339

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-61778-5

  • Online ISBN: 978-3-540-70678-6

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation