Binary and Multi-class Classification of Lexical Functions in Spanish Verb-Noun Collocations

  • Olga Kolesnikova
  • Alexander Gelbukh
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10633)


Collocations as semi-fixed lexical combinations present a challenge in natural language processing. While collocation identification on the shallow level is a task in which a significant advance has been reached, a deeper semantic representation and analysis of collocations remains an open issue. One of the possible solutions is detection of lexical functions of the Meaning-Text Theory in collocations thus resolving their semantic interpretation. We experimented with four lexical functions (Oper1, Real1, CausFunc0, and CausFunc1) for the special case of Spanish verb-noun collocations. In our experiments we also identified free verb-noun combinations as opposed to lexical functions. We used WordNet hypernyms as features and various algorithms of supervised machine learning; the best result with an F-measure of 0.873 was achieved for detecting Oper1 in binary classification.


Lexical functions Spanish verb-noun collocations Hypernyms Supervised learning 



The work was done under partial support of Mexican Government: SNI, BEIFI-IPN, and SIP-IPN grants 20172044 and 20172008.


  1. 1.
    Chen, W.T., Bonial, C., Palmer, M.: English light verb construction identification using lexical knowledge. In: AAAI, pp. 2368–2374 (2015)Google Scholar
  2. 2.
    Foufi, V., Nerima, L., Wehrli, E.: Parsing and MWE detection: fips at the PARSEME shared task. In: Proceedings of MWE (2017)Google Scholar
  3. 3.
    Gelbukh, A., Kolesnikova, O.: Supervised learning for semantic classification of Spanish collocations. In: Martínez-Trinidad, J.F., Carrasco-Ochoa, J.A., Kittler, J. (eds.) MCPR 2010. LNCS, vol. 6256, pp. 362–371. Springer, Heidelberg (2010). The lexical resource (lexical functions data) can be downloaded at or Scholar
  4. 4.
    Mel’čuk, I.A.: Lexical functions: a tool for the description of lexical relations in a Lexicon. In: Wanner, L. (ed.) Lexical Functions in Lexicography and Natural Language Processing, pp. 37–102. Benjamins Academic Publishers, Amsterdam (1996)Google Scholar
  5. 5.
    Miller, G.A., Leacock, C., Tengi, R., Bunker, R.T.: A semantic concordance. In: Proceedings of the Workshop on Human Language Technology Association for Computational Linguistics, pp. 303–308 (1993)Google Scholar
  6. 6.
    Nagy, I., Vincze, V.: Identifying verbal collocations in Wikipedia articles. In: Habernal, I., Matoušek, V. (eds.) TSD 2011. LNCS (LNAI), vol. 6836, pp. 179–186. Springer, Heidelberg (2011). Scholar
  7. 7.
    Pradhan, S.S., Hovy, E., Marcus, M., Palmer, M., Ramshaw, L., Weischedel, R.: Ontonotes: a unified relational semantic representation. Int. J. Semant. Comput. 1(04), 405–419 (2007)CrossRefGoogle Scholar
  8. 8.
    Rassi, A., Baptista, J., Mamede, N., Vale, O.: Integrating support verb constructions into a parser. In: Proceedings of Symposium in Information and Human Language Technology, Natal, RN, Brazil, 4–7 September, pp. 57–61 (2015)Google Scholar
  9. 9.
    Tutin, A.: Annotating lexical functions in corpora: showing collocations in context. In: Proceedings of the Second International Conference on the Meaning-Text Model (in Russian). Litres (2017)Google Scholar
  10. 10.
    Vincze, V., Zsibrita, J., Nagy, I.: Dependency parsing for identifying Hungarian light verb constructions. In: Proceedings of IJCNLP, pp. 207–215 (2013)Google Scholar
  11. 11.
    Witten, I.H., Frank, E., Hall, M.A.: Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann Publishers, MA, USA (2011)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Escuela Superior de CómputoInstituto Politécnico NacionalMexico CityMexico
  2. 2.Centro de Investigación en ComputaciónInstituto Politécnico NacionalMexico CityMexico

Personalised recommendations