Implications of an automatic lexical acquisition system

  • Peter M. Hastings
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1040)

Abstract

Camille, the Contextual Acquisition Mechanism for Incremental Lexeme LEarning, was implemented as an addition to Lytinen's LINK parser for use in an information extraction task, automatically inferring the meanings of unknown words from context. Unlike many previous lexical acquisition systems, Camille was thoroughly tested within a complex, real-world domain. The implementation of this system produced many lessons which are applicable to language learning in general. This paper describes Camille's implications for evaluation, for knowledge representation, and for cognitive modeling.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [Allen, 1981]
    J. Allen. What's necessary to hide?: Modeling action verbs. In Proceedings of the 19th Annual Meeting of the ACL, pages 77–81, 1981.Google Scholar
  2. [Behrend, 1990]
    D. Behrend. The development of verb concepts: Children's use of verbs to label familiar and novel events. Child Development, 61:681–696, 1990.PubMedGoogle Scholar
  3. [Brent, 1993]
    M. Brent. From grammar to lexicon: Unsupervised learning of lexical syntax. Computational Linguistics, 1993.Google Scholar
  4. [Cardie, 1993]
    C. Cardie. A case-based approach to knowledge acquisition for domainspecific sentence analysis. In Proceedings of the 11th National Conference on Artificial Intelligence, pages 798–803, 1993.Google Scholar
  5. [Chinchor, 1992]
    N. Chinchor. MUC-4 evaluation metrics. In Proceedings of the Fourth Message Understanding Conference, San Mateo, CA, 1992. Morgan Kaufmann Publishers, Inc.Google Scholar
  6. [Fernald and Morikawa, 1993]
    A. Fernald and H. Morikawa. Common themes and cultural variations in Japanese and American mothers' speech to infants. Child Development, 64:637–656, 1993.PubMedGoogle Scholar
  7. [Gentner, 1978]
    D. Gentner. On relational meaning: The acquisition of verb meaning. Child Development, 49:988–998, 1978.Google Scholar
  8. [Graesser et al., 1987]
    A. Graesser, P. Hopkinson, and C. Schmid. Differences in interconcept organization between nouns and verbs. Journal of Memory and Language, 26:242–253, 1987.Google Scholar
  9. [Granger, 1977]
    R. Granger. Foul-up: A program that figures out meanings of words from context. In Proceedings of Fifth International Joint Conference on Artificial Intelligence, 1977.Google Scholar
  10. [Hastings and Lytinen, 1994a]
    P. Hastings and S. Lytinen. Objects, actions, nouns, and verbs. In A. Ram and K. Eiselt, editors, Proceedings of the 16th Annual Conference of the Cognitive Science Society, pages 397–402, Hillsdale, NJ, 1994. Lawrence Erlbaum Associates.Google Scholar
  11. [Hastings and Lytinen, 1994b]
    P. Hastings and S. Lytinen. The ups and downs of lexical acquisition. In Proceedings of the 12th National Conference on Artificial Intelligence, pages 754–759, Cambridge, MA, 1994. MIT Press.Google Scholar
  12. [Hastings, 1994]
    P. Hastings. Automatic Acquisition of Word Meaning from Context. PhD thesis, University of Michigan, Ann Arbor, MI, 1994.Google Scholar
  13. [Hobbs et al., 1992]
    J. Hobbs, D. Appelt, M. Tyson, J. Bear, and D Israel. SRI International: Description of the FASTUS system used for MUC-4. In Proceedings of the Fourth Message Understanding Conference, San Mateo, CA, 1992. Morgan Kaufmann Publishers, Inc.Google Scholar
  14. [Huttenlocher and Lui, 1979]
    J. Huttenlocher and F. Lui. The semantic organization of some simple nouns and verbs. Journal of verbal learning and verbal behavior, 18:141–162, 1979.Google Scholar
  15. [Huttenlocher et al., 1991]
    J. Huttenlocher, W. Haight, A. Bryk, M. Seltzer, and T. Lyons. Early vocabulary growth: Relation to language input and gender. Developmental Psychology, 27(2):236–248, 1991.Google Scholar
  16. [Keil, 1991]
    F. Keil. Theories, concepts, and the acquisition of word meaning. In J. P. Byrnes and S. A. Gelman, editors, Perspectives on language and thought: Interrelations in development. Cambridge University Press, Cambridge, 1991.Google Scholar
  17. [Lytinen, 1991]
    S. Lytinen. A unification-based, integrated natural language processing system. Computers and Mathematics with Applications, 23(6–9):403–418, 1991.Google Scholar
  18. [MacGregor, 1990]
    R. MacGregor. The evolving technology of classification-based knowledge representation systems. In J. Sowa, editor, Principles of Semantic Nets: Explorations in the Representation of Knowledge. Morgan Kaufmann Publishers, San Mateo, CA, 1990.Google Scholar
  19. [Markman, 1991]
    E. Markman. The whole object, taxonomic, and mutual exclusivity assumptions as initial constraints on word meanings. In J. P. Byrnes and S. A. Gelman, editors, Perspectives on language and thought: Interrelations in development. Cambridge University Press, Cambridge, 1991.Google Scholar
  20. [Mitchell, 1977]
    T. Mitchell. Version spaces: A candidate elimination approach to rule learning. In Proceedings of the Fifth International Joint Conference on Artificial Intelligence, pages 305–309, 1977.Google Scholar
  21. [Riloff, 1993]
    E. Riloff. Automatically constructing a dictionary for information extraction tasks. In Proceedings of the 11th National Conference on Artificial Intelligence, pages 811–816, 1993.Google Scholar
  22. [Salveter, 1979]
    S. Salveter. Inferring conceptual graphs. Cognitive Science, 3:141–166, 1979.Google Scholar
  23. [Sundheim, 1992]
    B. Sundheim. Overview of the fourth message understanding evaluation and conference. In Proceedings of the Fourth Message Understanding Conference, San Mateo, CA, 1992. Morgan Kaufmann Publishers, Inc.Google Scholar
  24. [Zernik, 1987]
    Uri Zernik. How do machine language paradigms fare in language acquisition. In Proceedings of the Fourth International Workshop on Machine Learning, Los Altos, CA, 1987. Morgan Kaufmann.Google Scholar
  25. [Zernik, 1991]
    U. Zernik. Train1 vs. train2: Tagging word senses in corpus. In U. Zernik, editor, Lexical Acquisition: Exploiting On-line Resources to Build a Lexicon. Lawrence Erlbaum Associates, Inc, Hillsdale, NJ, 1991.Google Scholar

Copyright information

© Springer-Verlag 1996

Authors and Affiliations

  • Peter M. Hastings
    • 1
  1. 1.Artificial Intelligence LabThe University of MichiganAnn Arbor

Personalised recommendations