Advertisement

A Geometric Algebra Based Distributional Model to Encode Sentences Semantics

  • Agnese Augello
  • Manuel Gentile
  • Giovanni Pilato
  • Giorgio Vassallo
Chapter
Part of the Studies in Computational Intelligence book series (SCI, volume 515)

Abstract

Word space models are used to encode the semantics of natural language elements by means of high dimensional vectors [23]. Latent Semantic Analysis (LSA) methodology [15] is well known and widely used for its generalization properties. Despite of its good performance in several applications, the model induced by LSA ignores dynamic changes in sentences meaning that depend on the order of the words, because it is based on a bag of words analysis. In this chapter we present a technique that exploits LSA-based semantic spaces and geometric algebra in order to obtain a sub-symbolic encoding of sentences taking into account the words sequence in the sentence.

Keywords

Semantic spaces Sentences encoding Clifford algebra 

Notes

Acknowledgments

We are grateful to Professor Thomas Landauer, to Praful Mangalath and the Institute of Cognitive Science of the University of Colorado Boulder for providing us the TASA corpus. This work has been partially supported by the PON01_01687—SINTESYS (Security and INTElligence SYSstem) Research Project.

References

  1. 1.
    Agostaro, F., Pilato, G., Vassallo, G., Gaglio, S.: A sub-symbolic approach to word modelling for domain specific speech recognition. In: Proceedings of IEEE CAMP. International Workshop on Computer Architecture for Machine Perception, pp. 321–326 (2005)Google Scholar
  2. 2.
    Annesi, P., Storch, V., Basili, R.: Space projections as distributional models for semantic composition. In: Proceedings of the 13th International Conference on Computational Linguistics and Intelligent Text Processing - Volume Part I, CICLing’12, pp. 323–335. Springer, Heidelberg (2012)Google Scholar
  3. 3.
    Artin, E.: Geometric Algebra. Interscience Tracts in Pure and Applied Mathematics. Wiley, New York (1988)Google Scholar
  4. 4.
    Augello, A., Vassallo, G., Gaglio, S., Pilato, G.: Sentence induced transformations in "conceptual" spaces. In: IEEE Computer Society on Proceedings of the 2008 IEEE International Conference on Semantic Computing, ICSC ’08, pp. 34–41. Washington, USA (2008)Google Scholar
  5. 5.
    Baroni, M., Bernardini, S., Ferraresi, A., Zanchetta, E.: The wacky wide web: a collection of very large linguistically processed web-crawled corpora. Lang. Resour. Eval. 43, 209–226 (2009)Google Scholar
  6. 6.
    Basile, P., Caputo, A., Semeraro. G.: A study on compositional semantics of words in distributional spaces. In: 2012 IEEE Sixth International Conference on Semantic Computing (ICSC), pp. 154–161Google Scholar
  7. 7.
    Budiu, R., Royer, C., Pirolli, P.: Modeling information scent: a comparison of lsa, pmi and glsa similarity measures on common tests and corpora. In: Large Scale Semantic Access to Content (Text, Image, Video, and Sound), RIAO ’07, pp. 314–332. Paris, France (2007). Le Centre de Hautes Etudes Internationales d’informatique documentaireGoogle Scholar
  8. 8.
    Christopher, D.: Manning and Hinrich Schütze. Foundations of statistical natural language processing. MIT Press, USA (1999)Google Scholar
  9. 9.
    Clark, Stephen, Coecke, Bob, Sadrzadeh, Mehrnoosh: Mathematical foundations for a compositional distributed model of meaning. Linguist. Anal. 36(1–4), 345–384 (2011)Google Scholar
  10. 10.
    David, J.S.: Handbook of Parametric and Nonparametric Statistical Procedures. 3rd edn. Chapman & Hall/CRC (2003)Google Scholar
  11. 11.
    Dowty, D.R., Wall, R.E., Peters, S.: Introduction to Montague Semantics. vol. 11. D. Reidel, Dordrecht (1989)Google Scholar
  12. 12.
    Edward Grefenstette. Compositionality in distributional semantic models: A critical overview of current literature (2010)Google Scholar
  13. 13.
    GEMS Shared Evaluation. In: Proceedings of the GEMS 2011 Workshop on Geometrical Models of Natural Language Semantics, Association for Computational Linguistics. Edinburgh, UK (2011)Google Scholar
  14. 14.
    Hinrich, S.: Word space. In: Giles, L.C., Hanson, S.J., Cowan, J.D. (eds.) Advances in Neural Information Processing Systems 5, pp. 895–902. Morgan Kaufmann, San Francisco, CA (1993)Google Scholar
  15. 15.
    Landauer, T.K., Dumais, S.T.: Solutions to plato’s problem: The latent semantic analysis theory of acquisition, induction, and representation of knowledge. Psychol. Rev. 104 (1997)Google Scholar
  16. 16.
    Landauer, T.K., Foltz, P.W., Laham, D.: An introduction to latent semantic analysis. Discourse Process. 25, 259–284 (1998)CrossRefGoogle Scholar
  17. 17.
    Lounesto, P.: Clifford Algebra and Spinors. Cambridge University Press, Cambridge (1997)Google Scholar
  18. 18.
    Mitchell, J., Lapata, M.: Vector-based models of semantic composition. In: Proceedings of ACL-08: HLT, pp. 236–244. Columbus, Ohio (2008)Google Scholar
  19. 19.
    Mitchell, Jeff, Lapata, Mirella: Composition in distributional models of semantics. Cogn. Sci. 34(8), 1388–1429 (2010)CrossRefGoogle Scholar
  20. 20.
    Pilato, G., Augello, A., Gentile, M., Vassallo, G.: Geometric encoding of sentences based on clifford algebra. In: IC3K - KDIR 2012 - Proceedings of the International Conference on Knowledge Discovery and Information Retrieval - Special Session on Information Filtering and Retrieval: Novel Distributed Systems and Applications (DART). SciTePress, Barcelona (2012)Google Scholar
  21. 21.
    Rubenstein, Herbert, Goodenough, John B.: Contextual correlates of synonymy. Commun. ACM 8(10), 627–633 (October 1965)Google Scholar
  22. 22.
    Sahlgren, M.: The distributional hypothesis. From context to meaning: Distributional models of the lexicon in linguistics and cognitive science (Special issue of the Italian Journal of Linguistics) 20(1), 33–53 (2008)Google Scholar
  23. 23.
    Sahlgren, M.: The Word-Space Model. Ph.D. thesis, Stockholm University (2006). http://www.sics.se/mange/TheWordSpaceModel.pdf
  24. 24.
    Schoute, P.H.: Mehrdimensionale geometrie. Leipzig: G.J.Gschensche Verlagsha (Sammlung Schubert XXXV): Die linearen Rume, 1, 1902Google Scholar
  25. 25.
    Schütze, Hinrich: Automatic word sense discrimination. Comput. Linguist. 24(1), 97–123 (March 1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Agnese Augello
    • 1
  • Manuel Gentile
    • 2
  • Giovanni Pilato
    • 1
  • Giorgio Vassallo
    • 3
  1. 1.ICARPalermoItaly
  2. 2.ITDPalermoItaly
  3. 3.DICGIM Università di PalermoPalermoItaly

Personalised recommendations