Enhancing NLP Tasks by the Use of a Recent Neural Incremental Clustering Approach Based on Cluster Data Feature Maximization

  • Jean-Charles Lamirel
  • Ingrid Falk
  • Claire Gardent
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 198)


The IGNGF (Incremental Growing Neural Gas with Feature maximisation) method is a recent neural clustering method in which the use of a standard distance measure for determining a winner is replaced in IGNGF by cluster feature maximization. One main advantage of this method as compared to concurrent methods is that the maximized features used during learning can also be exploited in a final step for accurately labeling the resulting clusters. In this paper, we apply this method to the unsupervised classification of French verbs. We evaluate the obtained clusters (i.e., verb classes) in three different ways. The first one relies on an usual gold standard, the second one on unsupervised cluster quality indexes and the last one on a qualitative analysis. Our experiment illustrates that, conversely to former approaches for automatically acquiring verb classes, IGNGF method permits to produce relevant verb classes and to accurately associate the said classes with an explicit characterisation of the syntactic and semantic properties shared by the classes elements.


clustering NLP verb classification feature maximization incremental learning 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lamirel, J.C., Mall, R., Cuxac, P., Safi, G.: Variations to incremental growing neural gas algorithm based on label maximization. In: The 2011 International Joint Conference on Neural Networks (IJCNN), pp. 956–965 (2011)Google Scholar
  2. 2.
    Kipper, K., Dang, H.T., Palmer, M.: Class-based construction of a verb lexicon. In: AAAI/IAAI, pp. 691–696 (2000)Google Scholar
  3. 3.
    Dorr, B.J.: Large-scale dictionary construction for foreign language tutoring and interlingual machine translation. Machine Translation 12(4), 271–325 (1997)CrossRefGoogle Scholar
  4. 4.
    Prescher, D., Riezler, S., Rooth, M.: Using a probabilistic class-based lexicon for lexical ambiguity resolution. In: 18th International Conference on Computational Linguistics, Saarbrucken, Germany, pp. 649–655 (2000)Google Scholar
  5. 5.
    Korhonen, A.: Semantically motivated subcategorization acquisition. In: ACL Workshop on Unsupervised Lexical Acquisition, Philadelphia (2002)Google Scholar
  6. 6.
    Sun, L., Korhonen, A., Poibeau, T., Messiant, C.: Investigating the cross-linguistic potential of VerbNet-style classification. In: Proceedings of the 23rd International Conference on Computational Linguistics, COLING 2010, pp. 1056–1064. Association for Computational Linguistics, Stroudsburg (2010)Google Scholar
  7. 7.
    Schulte im Walde, S.: Experiments on the automatic induction of german semantic verb classes. Computational Linguistics 32(2), 159–194 (2006)CrossRefGoogle Scholar
  8. 8.
    Kipper Schuler, K.: VerbNet: A Broad-Coverage, Comprehensive Verb Lexicon. PhD thesis, University of Pennsylvania (2006)Google Scholar
  9. 9.
    Martinetz, T., Schulten, K.: A ”Neural-Gas” Network Learns Topologies. Artificial Neural Networks I, 397–402 (1991)Google Scholar
  10. 10.
    Fritzke, B.: A growing neural gas network learns topologies. In: Advances in Neural Information Processing Systems 7, pp. 625–632 (1995)Google Scholar
  11. 11.
    Prudent, Y., Ennaji, A.: An incremental growing neural gas learns topologies. In: Proceedings of the 2005 IEEE International Joint Conference on Neural Networks, IJCNN 2005, vol. 2, pp. 1211–1216 (2005)Google Scholar
  12. 12.
    Attik, M., Al Shehabi, S., Lamirel, J.C.: Clustering Quality Measures for Data Samples with Multiple Labels. In: Databases and Applications, pp. 58–65 (2006)Google Scholar
  13. 13.
    Ghribi, M., Cuxac, P., Lamirel, J.C., Lelu, A.: Mesures de qualité de clustering de documents: prise en compte de la distribution des mots clés. In: Béchet, N. (ed.) Évaluation des Méthodes d’Extraction de Connaissances dans les Données, EvalECD 2010, Hammamet, Tunisie, Fatiha Saïs, pp. 15–28 (January 2010)Google Scholar
  14. 14.
    van den Eynde, K., Mertens, P.: La valence : l’approche pronominale et son application au lexique verbal. Journal of French Language Studies 13, 63–104 (2003)CrossRefGoogle Scholar
  15. 15.
    Kupść, A., Abeillé, A.: Growing TreeLex. In: Gelbukh, A. (ed.) CICLing 2008. LNCS, vol. 4919, pp. 28–39. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  16. 16.
    Gross, M.: Méthodes en syntaxe. Hermann, Paris (1975)Google Scholar
  17. 17.
    Falk, I., Gardent, C., Lamirel, J.C.: Classifying French Verbs Using French and English Lexical Resources. In: ACL, pp. 207–214 (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Jean-Charles Lamirel
    • 1
  • Ingrid Falk
    • 1
  • Claire Gardent
    • 1
  1. 1.Campus ScientifiqueLORIAVandœuvre-lès-NancyFrance

Personalised recommendations