Predicting Reaction Times in Word Recognition by Unsupervised Learning of Morphology

  • Sami Virpioja
  • Minna Lehtonen
  • Annika Hultén
  • Riitta Salmelin
  • Krista Lagus
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6791)


A central question in the study of the mental lexicon is how morphologically complex words are processed. We consider this question from the viewpoint of statistical models of morphology. As an indicator of the mental processing cost in the brain, we use reaction times to words in a visual lexical decision task on Finnish nouns. Statistical correlation between a model and reaction times is employed as a goodness measure of the model. In particular, we study Morfessor, an unsupervised method for learning concatenative morphology. The results for a set of inflected and monomorphemic Finnish nouns reveal that the probabilities given by Morfessor, especially the Categories-MAP version, show considerably higher correlations to the reaction times than simple word statistics such as frequency, morphological family size, or length. These correlations are also higher than when any individual test subject is viewed as a model.


Training Corpus Mental Lexicon Complex Word Average Reaction Time Bigram Frequency 
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.
    Alegre, M., Gordon, P.: Frequency effects and the representational status of regular inflections. Journal of Memory and Language 40, 41–61 (1999)CrossRefGoogle Scholar
  2. 2.
    Bertram, R., Baayen, R., Schreuder, R.: Effects of family size for complex words. Journal of Memory and Language 42, 390–405 (2000)CrossRefGoogle Scholar
  3. 3.
    Butterworth, B.: Lexical representation. In: Butterworth, B. (ed.) Language Production, pp. 257–294. Academic Press, London (1983)Google Scholar
  4. 4.
    Chen, S.F., Goodman, J.: An empirical study of smoothing techniques for language modeling. Computer Speech & Language 13(4), 359–393 (1999)CrossRefGoogle Scholar
  5. 5.
    Creutz, M., Lagus, K.: Unsupervised morpheme segmentation and morphology induction from text corpora using Morfessor 1.0. Tech. Rep. A81. Publications in Computer and Information Science. Helsinki University of Technology (2005)Google Scholar
  6. 6.
    Creutz, M., Lagus, K.: Unsupervised models for morpheme segmentation and morphology learning. ACM Transactions on Speech and Language Processing 4(1) (January 2007)Google Scholar
  7. 7.
    Karlsson, F.: Suomen kielen äänne- ja muotorakenne (The Phonological and Morphological Structure of Finnish). Werner Söderström, Juva (1983)Google Scholar
  8. 8.
    Kurimo, M., Creutz, M., Varjokallio, M.: Morpho challenge evaluation using a linguistic gold standard. In: Peters, C., Jijkoun, V., Mandl, T., Müller, H., Oard, D.W., Peñas, A., Petras, V., Santos, D. (eds.) CLEF 2007. LNCS, vol. 5152, pp. 864–872. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  9. 9.
    Lehtonen, M., Cunillera, T., Rodríguez-Fornells, A., Hultén, A., Tuomainen, J., Laine, M.: Recognition of morphologically complex words in Finnish: evidence from event-related potentials. Brain Research 1148, 123–137 (2007)CrossRefGoogle Scholar
  10. 10.
    Lehtonen, M., Laine, M.: How word frequency affects morphological processing in monolinguals and bilinguals. Bilingualism: Language and Cognition 6, 213–225 (2003)CrossRefGoogle Scholar
  11. 11.
    Niemi, J., Laine, M., Tuominen, J.: Cognitive morphology in Finnish: foundations of a new model. Language and Cognitive Processes 9, 423–446 (1994)CrossRefGoogle Scholar
  12. 12.
    Quasthoff, U., Richter, M., Biemann, C.: Corpus portal for search in monolingual corpora. In: Proceedings of the Fifth International Conference on Language Resources and Evaluation, LREC 2006, Genoa, Italy, pp. 1799–1802 (2006)Google Scholar
  13. 13.
    Rissanen, J.: Modeling by shortest data description. Automatica 14, 465–471 (1978)CrossRefMATHGoogle Scholar
  14. 14.
    Siivola, V., Hirsimäki, T., Virpioja, S.: On growing and pruning Kneser-Ney smoothed n-gram models. IEEE Transactions on Audio, Speech & Language Processing 15(5), 1617–1624 (2007)CrossRefGoogle Scholar
  15. 15.
    Soveri, A., Lehtonen, M., Laine, M.: Word frequency and morphological processing revisited. The Mental Lexicon 2, 359–385 (2007)CrossRefGoogle Scholar
  16. 16.
    Taft, M.: Recognition of affixed words and the word frequency effect. Memory and Cognition 7, 263–272 (1979)CrossRefGoogle Scholar
  17. 17.
    Taft, M.: Morphological decomposition and the reverse base frequency effect. The Quarterly Journal of Experimental Psychology A 57, 745–765 (2004)CrossRefGoogle Scholar
  18. 18.
    The Department of General Linguistics, University of Helsinki and Research Institute for the Languages of Finland (gatherers): Finnish Parole Corpus (1996–1998), available through CSC,
  19. 19.
    Tiedemann, J.: News from OPUS — A collection of multilingual parallel corpora with tools and interfaces. In: Recent Advances in Natural Language Processing, vol. 5, pp. 237–248. John Benjamins, Amsterdam (2009)CrossRefGoogle Scholar
  20. 20.
    Vartiainen, J., Aggujaro, S., Lehtonen, M., Hultén, A., Laine, M., Salmelin, R.: Neural dynamics of reading morphologically complex words. NeuroImage 47, 2064–2072 (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Sami Virpioja
    • 1
  • Minna Lehtonen
    • 2
    • 3
    • 4
  • Annika Hultén
    • 3
    • 4
  • Riitta Salmelin
    • 3
  • Krista Lagus
    • 1
  1. 1.Department of Information and Computer ScienceAalto University School of ScienceFinland
  2. 2.Cognitive Brain Research Unit, Cognitive Science, Institute of Behavioural SciencesUniversity of HelsinkiFinland
  3. 3.Brain Research Unit, Low Temperature LaboratoryAalto University School of ScienceFinland
  4. 4.Department of Psychology and LogopedicsÅbo Akademi UniversityFinland

Personalised recommendations