Gradual Acquisition of Verb Selectional Preferences in a Bayesian Model

  • Afra Alishahi
  • Suzanne Stevenson
Part of the Theory and Applications of Natural Language Processing book series (NLP)


We present a cognitive model of inducing verb selectional preferences from individual verb usages. The selectional preferences for each verb argument are represented as a probability distribution over the set of semantic properties that the argument can possess—a semantic profile. The semantic profiles yield verb-specific conceptualizations of the arguments associated with a syntactic position. The proposed model can learn appropriate verb profiles from a small set of noisy training data, and can use them in simulating human plausibility judgments and analyzing implicit object alternation.


Semantic Property Direct Object Selectional Constraint Semantic Role Word Sense Disambiguation 
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.
    Abney, S., & Light, M. (1999). Hiding a semantic hierarchy in a Markov model. In Proceedings of the ACL workshop on unsupervised learning in natural language processing. Maryland, USA.Google Scholar
  2. 2.
    Alishahi, A., & Stevenson, S. (2007). A cognitive model for the representation and acquisition of verb selectional preferences. In Proceedings of the ACL-2007 workshop on cognitive aspects of computational language acquisition (pp. 41–48). Prague, Czech Republic.Google Scholar
  3. 3.
    Alishahi, A., & Stevenson, S. (2008). A computational model of early argument structure acquisition. Cognitive Science: A Multidisciplinary Journal, 32(5), 789–834.CrossRefGoogle Scholar
  4. 4.
    Alishahi, A., & Stevenson, S. (2010). A computational model of learning semantic roles from child-directed language. Language and Cognitive Processes, 25(1), 50–93.CrossRefGoogle Scholar
  5. 5.
    Anderson, J. R. (1991). The adaptive nature of human categorization. Psychological Review, 98(3), 409–429.CrossRefGoogle Scholar
  6. 6.
    Ciaramita, M., & Johnson, M. (2000). Explaining away ambiguity: Learning verb selectional preference with Bayesian networks. In Proceedings of the 18th international conference on computational linguistics (COLING 2000). Saarbrücken, Germany.Google Scholar
  7. 7.
    Clark, S., & Weir, D. (2002). Class-based probability estimation using a semantic hierarchy. Computational Linguistics, 28(2), 187–206.zbMATHCrossRefGoogle Scholar
  8. 8.
    Connor, M., Fisher, C., & Roth, D. (2012). Starting from scratch in semantic role labeling: Early indirect supervision. In Cognitive aspects of computational language acquisition. Springer.Google Scholar
  9. 9.
    Copestake, A., & Briscoe, T. (1991). Lexical operations in a unification-based framework. Lecture Notes in Computer Science, 627, 101–119.CrossRefGoogle Scholar
  10. 10.
    Devereux, B. J., Costello, F. J. (2012). Learning to interpret novel noun-noun compounds: Evidence from category learning experiments. In Cognitive aspects of computational language acquisition. Springer.Google Scholar
  11. 11.
    Erk, K. (2007). A simple, similarity-based model for selectional preferences. In Proceedings of the 45th annual meeting of the association of computational linguistics, pages 216–223, Prague, Czech Republic.Google Scholar
  12. 12.
    Gale, W. A., Church, K. W., & Yarowsky, D. (1992). Work on statistical methods for word sense disambiguation. In AAAI fall symposium on probabilistic approaches to natural language. Massachusetts, USAGoogle Scholar
  13. 13.
    Gleitman, L., & Gillette, J. (1995). The role of syntax in verb learning. In P. Fletcher, & B. MacWhinney (Eds.), Handbook of child language. Oxford: Blackwell.Google Scholar
  14. 14.
    Holmes, V. M., Stowe, L., & Cupples, L. (1989). Lexical expectations in parsing complement-verb sentences. Journal of Memory and Language, 28, 668–689.CrossRefGoogle Scholar
  15. 15.
    Jackendoff, R. (1983). Semantics and cognition. Cambridge, MA: MIT.Google Scholar
  16. 16.
    Johansson, R., & Nugues, P. (2007). Extended constituent-to-dependency conversion for English. In Proceedings of NODALIDA 2007, Tartu, Estonia (pp. 105–112).Google Scholar
  17. 17.
    Katz, J., & Fodor, J. (1964). The structure of language: Readings in the philosophy of language. Englewood Cliffs, N.J., Prentice Hall.Google Scholar
  18. 18.
    Li, H., & Abe, N. (1998). Generalizing case frames using a thesaurus and the MDL principle. Computational Linguistics, 24(2), 217–244.Google Scholar
  19. 19.
    Light, M., & Greiff, W. (2002). Statistical models for the induction and use of selectional preferences. Cognitive Science, 26(3), 269–281.CrossRefGoogle Scholar
  20. 20.
    MacWhinney, B. (2000). The CHILDES project: Tools for analyzing talk (3rd ed.). Mahwah, NJ: Lawrence Erlbaum Associates.Google Scholar
  21. 21.
    Marcus, M., Marcinkiewicz, M., & Santorini, B. (1993). Building a large annotated corpus of English: The Penn Treebank. Computational linguistics, 19(2), 330.Google Scholar
  22. 22.
    McCarthy, D., & Carroll, J. (2003). Disambiguating nouns, verbs, and adjectives using automatically acquired selectional preferences. Computational Linguistics, 29(4), 639–654.zbMATHCrossRefGoogle Scholar
  23. 23.
    Miller, G. (1990). WordNet: An on-line lexical database. International Journal of Lexicography, 17(3), 235–244CrossRefGoogle Scholar
  24. 24.
    Nation, K., Marshall, C. M., & Altmann, G. T. M. (2003). Investigating individual differences in children’s real-time sentence comprehension using language-mediated eye movements. Journal of Experimental Child Psychology, 86, 314–329.CrossRefGoogle Scholar
  25. 25.
    Nematzadeh, A., Fazly, A., & Stevenson, S. (2012). Child acquisition of multiword verbs: A computational investigation. In Cognitive Aspects of Computational Language Acquisition. Springer.Google Scholar
  26. 26.
    Pinker, S. (1994). How could a child use verb syntax to learn verb semantics? Lingua, 92, 377–410.CrossRefGoogle Scholar
  27. 27.
    Pustejovsky, J. (1995). The generative lexicon. Cambridge, MA: MIT.Google Scholar
  28. 28.
    Resnik, P. (1993). Selection and information: A class-based approach to lexical relationships. PhD thesis, University of Pennsylvania.Google Scholar
  29. 29.
    Resnik, P. (1996). Selectional constraints: An information-theoretic model and its computational realization. Cognition, 61, 127–199.CrossRefGoogle Scholar
  30. 30.
    Resnik, P. (1997). Selectional preference and sense disambiguation. In Proceedings of the ACL SIGLEX workshop on tagging text with lexical semantics: Why, What, and How? Washington, D.C., USA.Google Scholar
  31. 31.
    Schütze, H. (1992). Context space. In AAAI fall symposium on probabilistic approaches to natural language. Massachusetts, USA.Google Scholar
  32. 32.
    Zapirain, B., Agirre, E., & Màrquez, L. (2009). Generalizing over lexical features: Selectional preferences for semantic role classification. In Proceedings of the ACL-IJCNLP 2009 conference short papers, (pp. 73–76). Association for Computational Linguistics.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.Department of Communication and Information StudiesTilburg UniversityTilburgThe Netherlands
  2. 2.Department of Computer ScienceUniversity of TorontoTorontoCanada

Personalised recommendations