Parsing with Lexicalized Probabilistic Recursive Transition Networks

  • Alexis Nasr
  • Owen Rambow
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4002)


We present a formalization of lexicalized Recursive Transition Networks which we call Automaton-Based Generative Dependency Grammar (gdg). We show how to extract a gdg from a syntactically annotated corpus, present a chart parser for gdg, and discuss different probabilistic models which are directly implemented in the finite automata and do not affect the parser.


Dependency Tree Derivation Tree Elementary Tree Auxiliary Tree Parsing Algorithm 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Rambow, O., Bangalore, S., Butt, T., Nasr, A., Sproat, R.: Creating a finite-state parser with application semantics. In: Proceedings of the 19th International Conference on Computational Linguistics (COLING 2002), Taipei, Republic of China (2002)Google Scholar
  2. 2.
    Woods, W.A.: Transition network grammars for natural language analysis. Commun. ACM 3, 591–606 (1970)CrossRefzbMATHGoogle Scholar
  3. 3.
    Hays, D.G.: Dependency theory: A formalism and some observations. Language 40, 511–525 (1964)CrossRefGoogle Scholar
  4. 4.
    Gaifman, H.: Dependency systems and phrase-structure systems. Information and Control 8, 304–337 (1965)MathSciNetCrossRefzbMATHGoogle Scholar
  5. 5.
    Abney, S.: A grammar of projections. Universität Tübingen (unpublished manuscript) (1996)Google Scholar
  6. 6.
    Madsen, O., Kristensen, B.: LR-parsing of extended context-free grammars. Acta Informatica 7, 61–73 (1976)MathSciNetCrossRefzbMATHGoogle Scholar
  7. 7.
    Lombardo, V.: An Earley-style parser for dependency grammars. In: Proceedings of the 16th International Conference on Computational Linguistics (COLING 1996), Copenhagen (1996)Google Scholar
  8. 8.
    Nasr, A., Rambow, O.: Supertagging and full parsing. In: Proceedings of the Workshop on Tree Adjoining Grammar and Related Formalisms (TAG+7), Vancouver, BC, Canada (2004)Google Scholar
  9. 9.
    Alshawi, H., Bangalore, S., Douglas, S.: Learning dependency translation models as collections of finite-state head transducers. cl 26, 45–60 (2000)MathSciNetGoogle Scholar
  10. 10.
    Eisner, J.M.: Three new probabilistic models for dependency parsing: An exploration. In: Proceedings of the 16th International Conference on Computational Linguistics (COLING 1996), Copenhagen (1996)Google Scholar
  11. 11.
    Bangalore, S., Joshi, A.: Supertagging: An approach to almost parsing. Computational Linguistics 25, 237–266 (1999)Google Scholar
  12. 12.
    Chen, J.: Towards Efficient Statistical Parsing Using Lexicalized Grammatical Information. PhD thesis, University of Delaware (2001)Google Scholar
  13. 13.
    Xia, F., Palmer, M., Joshi, A.: A uniform method of grammar extraction and its applications. In: Proc. of the EMNLP 2000, Hong Kong (2000)Google Scholar
  14. 14.
    Chiang, D.: Statistical parsing with an automatically-extracted tree adjoining grammar. In: 38th Meeting of the Association for Computational Linguistics (ACL 2000), Hong Kong, China, pp. 456–463 (2000)Google Scholar
  15. 15.
    Schabes, Y., Waters, R.C.: Tree Insertion Grammar: A cubic-time, parsable formalism that lexicalizes Context-Free Grammar without changing the trees produced. Computational Linguistics 21, 479–514 (1995)MathSciNetGoogle Scholar
  16. 16.
    Nasr, A.: Analyse syntaxique probabiliste pour grammaires de dTpendances extraites automatiquement. Habilitation a diriger des recherches, UniversitT Paris 7 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Alexis Nasr
    • 1
  • Owen Rambow
    • 2
  1. 1.Lattice-CNRS (UMR 8094)Université Paris 7ParisFrance
  2. 2.Center for Computational Learning SystemsColumbia UniversityNew YorkUSA

Personalised recommendations