Detection of Semantic Compositionality Using Semantic Spaces

  • Lubomír Krčmář
  • Karel Ježek
  • Massimo Poesio
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7499)

Abstract

Any Natural Language Processing (NLP) system that does semantic processing relies on the assumption of semantic compositionality: the meaning of a compound is determined by the meaning of its parts and their combination. However, the compositionality assumption does not hold for many idiomatic expressions such as “blue chip”. This paper focuses on the fully automatic detection of these, further referred to as non-compositional compounds.

We have proposed and tested an intuitive approach based on replacing the parts of compounds by semantically related words. Our models determining the compositionality combine simple statistic ideas with the COALS semantic space. For the evaluation, the shared dataset for the Distributional Semantics and Compositionality 2011 workshop (DISCO 2011) is used. A comparison of our approach with the traditionally used Pointwise Mutual Information (PMI) is also presented. Our best models outperform all the systems competing in DISCO 2011.

Keywords

DISCO 2011 compositionality semantic space collocations COALS PMI 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Firth, J.R.: A synopsis of linguistic theory 1930–1955. Studies in Linguistic Analysis (special volume of the Philological Society) 1952-59, 1–32 (1957)Google Scholar
  2. 2.
    Biemann, C., Giesbrecht, E.: Distributional Semantics and Compositionality 2011: Shared Task Description and Results. In: Proceedings of the Workshop on Distributional Semantics and Compositionality, pp. 21–28 (2011)Google Scholar
  3. 3.
    Turney, P.D., Pantel, P.: From Frequency to Meaning: Vector Space Models of Semantics. Artificial Intelligence Research 37, 141–188 (2010)MathSciNetMATHGoogle Scholar
  4. 4.
    Rohde, D.L.T., Gonnerman, L.M., Plaut, D.C.: An Improved Model of Semantic Similarity Based on Lexical (2005) (unpublished manuscript)Google Scholar
  5. 5.
    Jurgens, D., Stevens, K.: The S-Space Package: An Open Source Package for Word Space Models. In: Proc. of the ACL 2010 System Demonstrations, pp. 30–35 (2010)Google Scholar
  6. 6.
    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
  7. 7.
    Johannsen, A., Martinez, H.: Rishøj, C., Søgaard, A.: Shared task system description: Frustratingly hard compositionality prediction. In: Proceedings of the Workshop on Distributional Semantics and Compositionality, pp. 29–32 (2011)Google Scholar
  8. 8.
    Lin, D.: Automatic Identification of Non-compositional Phrases. In: Proceedings of the 37th Annual Meeting of the ACL on Computational Linguistics, vol. 37, pp. 317–324 (1999)Google Scholar
  9. 9.
    Chakraborty, T., Pal, S., Mondal, T., Saikh, T.: Shared task system description: Measuring the Compositionality of Bigrams using Statistical Methodologies. In: Proc. of the Workshop on Distributional Semantics and Compositionality, pp. 38–42 (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Lubomír Krčmář
    • 1
  • Karel Ježek
    • 1
  • Massimo Poesio
    • 2
  1. 1.Faculty of Applied SciencesUniversity of West BohemiaCzech Republic
  2. 2.University of EssexUnited Kingdom

Personalised recommendations