Space Projections as Distributional Models for Semantic Composition

  • Paolo Annesi
  • Valerio Storch
  • Roberto Basili
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7181)


Empirical distributional methods account for the meaning of syntactic structures by combining word vectors according to algebraic operators. In this paper, a novel approach for semantic composition based on space projection techniques over lexical vector representations is proposed. In line with the principle of compositionality, the meaning of a phrase is modeled in terms of the subset of properties shared by co-occurring words. Syntactic bi-grams are thus projected in the so called Support Subspace, corresponding to such properties. State-of-the-art results are achieved in a well known phrase similarity task, used as a benchmark for this class of methods.


Target Word Space Projection Word Pair Latent Semantic Analysis Vector Space Model 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Montague, R.: Formal Philosophy: Selected Papers of Richard Montague. Yale University Press (1974)Google Scholar
  2. 2.
    Coecke, B., Ssdrzaden, M., Clark, S.: Mathematical foundations for a compositional distributed model of meaning. Lambek Festschrift, Linguistic Analysis 36 (2010)Google Scholar
  3. 3.
    Firth, J.: A synopsis of linguistic theory 1930-1955. In: Studies in Linguistic Analysis. Philological Society, Oxford (1957); reprinted in Palmer, F. (ed.) Selected Papers of J. R. Firth. Longman, Harlow (1968)Google Scholar
  4. 4.
    Schütze, H.: Automatic Word Sense Discrimination. Computational Linguistics 24, 97–124 (1998)Google Scholar
  5. 5.
    Wittgenstein, L.: Philosophical Investigations. Blackwells, Oxford (1953)Google Scholar
  6. 6.
    Schütze, H.: Word space. In: Hanson, S.J., Cowan, J.D., Giles, C.L. (eds.) NIPS 5, pp. 895–902. Morgan Kaufmann Publishers, San Mateo (1993)Google Scholar
  7. 7.
    Turney, P.D., Pantel, P.: From frequency to meaning: Vector space models of semantics. Journal of Artificial Intelligence Research 37, 141 (2010)MathSciNetzbMATHGoogle Scholar
  8. 8.
    Mitchell, J., Lapata, M.: Vector-based models of semantic composition. In: Proceedings of ACL/HLT 2008, pp. 236–244 (2008)Google Scholar
  9. 9.
    Baroni, M., Zamparelli, R.: Nouns are vectors, adjectives are matrices: representing adjective-noun constructions in semantic space. In: EMNLP 2010, pp. 1183–1193. Association for Computational Linguistics, Stroudsburg (2010)Google Scholar
  10. 10.
    Grefenstette, E., Sadrzadeh, M.: Experimental support for a categorical compositional distributional model of meaning. CoRR abs/1106.4058 (2011)Google Scholar
  11. 11.
    Salton, G., Wong, A., Yang, C.: A vector space model for automatic indexing. Communications of the ACM 18, 613–620 (1975)zbMATHCrossRefGoogle Scholar
  12. 12.
    Deerwester, S.C., Dumais, S.T., Landauer, T.K., Furnas, G.W., Harshman, R.A.: Indexing by latent semantic analysis. Journal of The American Society For Information Science 41, 391–407 (1990)CrossRefGoogle Scholar
  13. 13.
    Landauer, T.K., Dutnais, S.T.: A solution to plato’s problem: The latent semantic analysis theory of acquisition, induction, and representation of knowledge. Psychological Review, 211–240 (1997)Google Scholar
  14. 14.
    Harris, Z.S.: Mathematical Structures of Language. Wiley, NY (1968)zbMATHGoogle Scholar
  15. 15.
    Lin, D.: Automatic retrieval and clustering of similar word. In: Proceedings of COLING-ACL, Montreal, Canada (1998)Google Scholar
  16. 16.
    Pantel, P., Lin, D.: Document clustering with committees. In: Proceedigs of SIGIR 2002, Montreal, Canada, pp. 199–206 (2002)Google Scholar
  17. 17.
    Pennacchiotti, M., Cao, D.D., Basili, R., Croce, D., Roth, M.: Automatic induction of framenet lexical units. In: EMNLP, pp. 457–465 (2008)Google Scholar
  18. 18.
    Croce, D., Giannone, C., Annesi, P., Basili, R.: Towards open-domain semantic role labeling. In: Proceedings of ACL, pp. 237–246 (2010)Google Scholar
  19. 19.
    Foltz, P.W., Kintsch, W., Landauer, T.K.: The measurement of textual coherence with latent semantic analysis. Discourse Processes 25, 285–307 (1998)CrossRefGoogle Scholar
  20. 20.
    Erk, K., Pad, S.: A structured vector space model for word meaning in context. In: EMNLP 2008: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 897–906. ACL (2008)Google Scholar
  21. 21.
    Mitchell, J., Lapata, M.: Composition in distributional models of semantics. Cognitive Science 34, 1388–1429 (2010)CrossRefGoogle Scholar
  22. 22.
    Baroni, M., Bernardini, S., Ferraresi, A., Zanchetta, E.: The wacky wide web: a collection of very large linguistically processed web-crawled corpora. Language Resources And Evaluation 43, 209–226 (2009)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Paolo Annesi
    • 1
  • Valerio Storch
    • 1
  • Roberto Basili
    • 1
  1. 1.Department of Enterprise EngineeringUniversity of Roma Tor VergataRomaItaly

Personalised recommendations