Advertisement

A Compositional Distributional Semantics, Two Concrete Constructions, and Some Experimental Evaluations

  • Mehrnoosh Sadrzadeh
  • Edward Grefenstette
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7052)

Abstract

We provide an overview of the hybrid compositional distributional model of meaning, developed in [6], which is based on the categorical methods also applied to the analysis of information flow in quantum protocols. The mathematical setting stipulates that the meaning of a sentence is a linear function of the tensor products of the meanings of its words. We provide concrete constructions for this definition and present techniques to build vector spaces for meaning vectors of words, as well as that of sentences. The applicability of these methods is demonstrated via a toy vector space as well as real data from the British National Corpus and two disambiguation experiments.

Keywords

Logic Natural Language Vector Spaces Tensor Product Composition Distribution Compact Categories Pregroups 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Abramsky, S., Coecke, B.: A categorical semantics of quantum protocols. In: Proceedings of the 19th Annual IEEE Symposium on Logic in Computer Science (2004)Google Scholar
  2. 2.
    Alshawi, H. (ed.): The Core Language Engine. MIT Press, Cambridge (1992)Google Scholar
  3. 3.
    Baroni, M., Zamparelli, R.: Nouns are vectors, adjectives are matrices. In: Proceedings of Conference on Empirical Methods in Natural Language Processing, EMNLP (2010)Google Scholar
  4. 4.
    Bruza, P., Kitto, K., Nelson, D.L., McEvoy, C.L.: Entangling words and meaning. In: Proceedings of AAAI Spring Symposium on Quantum Interaction. Oxford University, College Publications (2008)Google Scholar
  5. 5.
    Clark, S., Pulman, S.: Combining Symbolic and Distributional Models of Meaning. In: Proceedings of AAAI Spring Symposium on Quantum Interaction. Standord University, AAAI Press (2007)Google Scholar
  6. 6.
    Coecke, B., Sadrzadeh, M., Clark, S.: Mathematical Foundations for Distributed Compositional Model of Meaning. In: van Benthem, J., Moortgat, M., Buszkowski, W. (eds.) Lambek Festschrift. Linguistic Analysis, vol. 36, pp. 345–384 (2010); arXiv:1003.4394v1 [cs.CL]Google Scholar
  7. 7.
    Curran, J.: From Distributional to Semantic Similarity. PhD Thesis, University of Edinburgh (2004)Google Scholar
  8. 8.
    Firth, J.R.: A synopsis of linguistic theory 1930-1955. Studies in Linguistic Analysis (1957)Google Scholar
  9. 9.
    Grefenstette, E., Sadrzadeh, M., Clark, S., Coecke, B., Pulman, S.: Concrete Compositional Sentence Spaces for a Compositional Distributional Model of Meaning. In: International Conference on Computational Semantics (IWCS 2011), Oxford (2011); arXiv:1101.0309v1 [cs.CL]Google Scholar
  10. 10.
    Grefenstette, E., Sadrzadeh, M.: Experimental Support for a Categorical Compositional Distributional Model of Meaning. In: Empirical Methods in Natural Language Processing (EMNLP 2011), Edinburgh (2011)Google Scholar
  11. 11.
    Grefenstette, G.: Explorations in Automatic Thesaurus Discovery. Kluwer, Dordrecht (1994)CrossRefMATHGoogle Scholar
  12. 12.
    Guevara, E.: A Regression Model of Adjective-Noun Compositionality in Distributional Semantics. In: Proceedings of the ACL GEMS Workshop (2010)Google Scholar
  13. 13.
    Lambek, J.: From Word to Sentence. Polimetrica, Milan (2008)Google Scholar
  14. 14.
    Landauer, T., Dumais, S.: A solution to Platos problem: The latent semantic analysis theory of acquisition, induction, and representation of knowledge. Psychological Review (2008)Google Scholar
  15. 15.
    Manning, C.D., Raghavan, P., Schütze, H.: Introduction to information retrieval. Cambridge University Press, Cambridge (2008)Google Scholar
  16. 16.
    Mitchell, J., Lapata, M.: Vector-based models of semantic composition. In: Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics, pp. 236–244 (2008)Google Scholar
  17. 17.
    Montague, R.: English as a formal language. Formal Philosophy, 189–223 (1974)Google Scholar
  18. 18.
    Nivre, J.: An efficient algorithm for projective dependency parsing. In: Proceedings of the 8th International Workshop on Parsing Technologies, IWPT (2003)Google Scholar
  19. 19.
    van Rijsbergen, K.: The Geometry of Information Retrieval. Cambridge University Press, Cambridge (2004)CrossRefMATHGoogle Scholar
  20. 20.
    Saffron, J., Newport, E., Asling, R.: Word Segmentation: The role of distributional cues. Journal of Memory and Language 35, 606–621 (1999)CrossRefGoogle Scholar
  21. 21.
    Schuetze, H.: Automatic Word Sense Discrimination. Computational Linguistics 24, 97–123 (1998)Google Scholar
  22. 22.
    Widdows, D.: Geometry and Meaning. University of Chicago Press, Chicago (2005)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Mehrnoosh Sadrzadeh
    • 1
  • Edward Grefenstette
    • 1
  1. 1.Department of Computer ScienceUniversity of OxfordUK

Personalised recommendations