Experiments and Results with Diacritics Restoration in Romanian

  • Cristian Grozea
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7499)


The purpose of this paper is (1) to make an extensive overview of the field of diacritics restoration in Romanian texts, (2) to present our own experiments and results and to promote the use of the word-based Viterbi algorithm as a better accuracy solution used already in a free web-based TTS implementation, (3) to announce the production of a new, high-quality, high-volume corpus of Romanian texts, twice the size of the Romanian language subset of the JRC-Acquis.


Ambiguous Word Word Sense Word Sense Disambigua Computational Linguistics Letter Level 
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.
    Tufiş, D., Chiţu, A.: Automatic diacritics insertion in Romanian texts. In: Proceedings of COMPLEX 1999 International Conference on Computational Lexicography (1999)Google Scholar
  2. 2.
    Tufiş, D., Ceauşu, A.: Diacritics Restoration in Romanian Texts. In: Pascaleva, E., Slavcheva, M. (eds.) A Common Natural Language Processing Paradigm for Balkan Languages, pp. 49–55 (2007)Google Scholar
  3. 3.
    Mihalcea, R.F.: Diacritics Restoration: Learning from Letters versus Learning from Words. In: Gelbukh, A. (ed.) CICLing 2002. LNCS, vol. 2276, pp. 339–348. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  4. 4.
    Mihalcea, R., Năstase, V.: Letter level learning for language independent diacritics restoration. In: International Conference on Computational Linguistics, pp. 1–7. Association for Computational Linguistics, Morristown (2002)CrossRefGoogle Scholar
  5. 5.
    De Pauw, G., Wagacha, P.W., de Schryver, G.-M.: Automatic Diacritic Restoration for Resource-Scarce Languages. In: Matoušek, V., Mautner, P. (eds.) TSD 2007. LNCS (LNAI), vol. 4629, pp. 170–179. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  6. 6.
    Tufis, D., Ceausu, A.: Diac+: a professional diacritics recovering system. In: LREC, European Language Resources Association (2008)Google Scholar
  7. 7.
    Bobicev, V.: Statistical Methods and Algorithms of Text Processing (based on Romanian texts). Ph.D. thesis, Technical University of Moldova (2007)Google Scholar
  8. 8.
    Steinberger, R., Pouliquen, B., Widiger, A., Ignat, C., Erjavec, T., Tufis, D., Varga, D.: The JRC-acquis: A multilingual aligned parallel corpus with 20+ languages. In: Proceedings of the 5th International Conference on Language Resources and Evaluation, LREC 2006, Genoa, Italy (2006)Google Scholar
  9. 9.
    Viterbi, A.: Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. Information Theory 13, 260–269 (1967)zbMATHCrossRefGoogle Scholar
  10. 10.
    Grozea, C.: Finding optimal parameter settings for high performance word sense disambiguation. In: Proceedings of Senseval-3: The Third International Workshop on the Evaluation of Systems for the Semantic Analysis of Text (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Cristian Grozea
    • 1
  1. 1.Fraunhofer Institute FIRSTBerlinGermany

Personalised recommendations