Romanian Syllabication Using Machine Learning

  • Liviu P. Dinu
  • Vlad Niculae
  • Octavia-Maria Sulea
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8082)


The task of finding syllable boundaries can be straightforward or challenging, depending on the language. Text-to-speech applications have been shown to perform considerably better when syllabication, whether orthographic or phonetic, is employed as a means of breaking down the text into units bellow word level. Romanian syllabication is non-trivial mainly but not exclusively due to its hiatus-diphthong ambiguity. This phenomenon affects both phonetic and orthographic syllabication. In this paper, we focus on orthographic syllabication for Romanian and show that the task can be carried out with a high degree of accuracy by using sequence tagging. We compare this approach to support vector machines and rule-based methods. The features we used are simply character n-grams with end-of-word marking.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bartlett, S., Kondrak, G., Cherry, C.: Automatic syllabification with structured svms for letter to phoneme conversion. In: 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL 2008: HLT), pp. 568–576. Association for Computational Linguistics, Columbus (2008)Google Scholar
  2. 2.
    Collective: Collective: Dictionarul ortografic, ortoepic si morfologic al limbii române., 2nd edn., revised. Romanian Academy, Bucharest (2010) (in Romanian)Google Scholar
  3. 3.
    Trogkanis, N., Elkan, C.: Conditional Random Fields for word hyphenation. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pp. 366–374. Association for Computational Linguistics, Uppsala (2010)Google Scholar
  4. 4.
    Toma, S.A., Oancea, E., Munteanu, D.: Automatic rule-based syllabication for Romanian. In: Proceedings of the 5th Conference on Speech Technology and Human-Computer Dialogue (2009)Google Scholar
  5. 5.
    Dinu, A., Dinu, L.P.: A parallel approach to syllabification. In: Gelbukh, A. (ed.) CICLing 2005. LNCS, vol. 3406, pp. 83–87. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  6. 6.
    Chitoran, I., Hualde, J.I.: From hiatus to diphthong: the evolution of vowel sequences in romance. Phonology 24, 37–75 (2007)CrossRefGoogle Scholar
  7. 7.
    Lafferty, J.D., McCallum, A., Pereira, F.C.N.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: Proceedings of the Eighteenth International Conference on Machine Learning. ICML 2001, pp. 282–289. Morgan Kaufmann Publishers Inc., San Francisco (2001)Google Scholar
  8. 8.
    Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E.: Scikit-learn: Machine learning in Python. Journal of Machine Learning Research 12, 2825–2830 (2011)Google Scholar
  9. 9.
    Okazaki, N.: CRFsuite: a fast implementation of Conditional Random Fields (CRFs) (2007)Google Scholar
  10. 10.
    Barbu, A.M.: Romanian lexical databases: Inflected and syllabic forms dictionaries. In: Sixth International Language Resources and Evaluation (LREC 2008) (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Liviu P. Dinu
    • 1
    • 2
  • Vlad Niculae
    • 1
    • 3
  • Octavia-Maria Sulea
    • 1
    • 2
  1. 1.Center for Computational LinguisticsUniversity of BucharestRomania
  2. 2.Faculty of Mathematics and Computer ScienceUniversity of BucharestRomania
  3. 3.University of WolverhamptonUK

Personalised recommendations