A Generative Model for Semantic Role Labeling

  • Cynthia A. Thompson
  • Roger Levy
  • Christopher D. Manning
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2837)


Determining the semantic role of sentence constituents is a key task in determining sentence meanings lying behind a veneer of variant syntactic expression. We present a model of natural language generation from semantics using the FrameNet semantic role and frame ontology. We train the model using the FrameNet corpus and apply it to the task of automatic semantic role and frame identification, producing results competitive with previous work (about 70% role labeling accuracy). Unlike previous models used for this task, our model does not assume that the frame of a sentence is known, and is able to identify null-instantiated roles, which commonly occur in our corpus and whose identification is crucial to natural language interpretation.


Machine Translation Semantic Role Statistical Machine Translation Lexical Unit Natural Language Generation 
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.


  1. 1.
    Baker, C.F., Fillmore, C.J., Lowe, J.B.: The Berkeley FrameNet project. In: COLING-ACL (1998) Google Scholar
  2. 2.
    Gildea, D., Jurafsky, D.: Automatic labeling of semantic roles. Computational Linguistics 28, 245–288 (2002)CrossRefGoogle Scholar
  3. 3.
    Riloff, E., Jones, R.: Learning dictionaries for information extraction by multi-level bootstrapping. In: Sixteenth National Conference on Artificial Intelligence, pp. 474–479 (1999)Google Scholar
  4. 4.
    Nigam, K., McCallum, A.K., Thrun, S., Mitchell, T.M.: Learning to classify text from labeled and unlabeled documents. In: Proceedings of AAAI 1998, 15th Conference of the American Association for Artificial Intelligence, Madison, pp. 792–799. AAAI Press, Menlo Park (1998)Google Scholar
  5. 5.
    Freitag, D., McCallum, A.: Information extraction with HMM structures learned by stochastic optimization. In: Proceedings of AAAI, pp. 584–589 (2000)Google Scholar
  6. 6.
    Leek, T.: Information extraction using hidden Markov models. Master’s thesis, UC San Diego (1997)Google Scholar
  7. 7.
    Huffman, S.: Learning information extraction patterns from examples. In: Wermter, S., Scheler, G., Riloff, E. (eds.) Connectionist, Statistical and Symbolic Approaches to Learning for Natural Language Processing, pp. 246–260. Springer, Heidelberg (1996)Google Scholar
  8. 8.
    Resnik, P.S.: Selection and Information: a class-based approach to lexical relationships. PhD thesis, University of Pennsylvania (1993)Google Scholar
  9. 9.
    Rooth, M., Riezler, S., Prescher, D., Carroll, G., Beil, F.: Inducing a semantically annotated lexicon via em-based clustering. In: 37th Annual Meeting of the ACL (1999) Google Scholar
  10. 10.
    Kingsbury, P., Palmer, M., Marcus, M.: Adding semantic annotation to the penn treebank. In: Proceedings of the Human Language Technology Conference, San Diego, California (2002)Google Scholar
  11. 11.
    Collins, M.J.: Three generative, lexicalised models for statistical parsing. ACL 35/EACL 8, 16–23 (1997)Google Scholar
  12. 12.
    Collins, M.: Head-Driven Statistical Models for Natural Language Parsing. PhD thesis, University of Pennsylvania (1999)Google Scholar
  13. 13.
    Cowell, R.G., Dawid, A.P., Lauritzen, S.L., Spiegelhalter, D.J.: Probabilistic Networks and Expert Systems. Springer, New York (1999)zbMATHGoogle Scholar
  14. 14.
    Klein, D., Manning, C.D.: Fast exact inference with a factored model for natural language parsing. In: Advances in Neural Information Processing Systems, vol. 15, MIT Press, Cambridge (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Cynthia A. Thompson
    • 1
  • Roger Levy
    • 2
  • Christopher D. Manning
    • 2
  1. 1.School of ComputingUniversity of UtahSalt Lake CityUSA
  2. 2.Departments of Linguistics and Computer ScienceStanford UniversityStanfordUSA

Personalised recommendations