NEBEL: Never-Ending Bilingual Equivalent Learner

  • Thiago Lima Vieira
  • Helena de Medeiros Caseli
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8856)


In this paper, we present NEBEL: an automatic system able to learn bilingual equivalents (translations) using the never-ending machine learning (NEML) strategy. Motivated by the way humans learn, the NEML is a continuous learning strategy which uses the knowledge already acquired to learn new information and, therefore, to improve its performance. The NEML was chosen to be applied in our context because it has two desirable features to deal with our intended problem: (i) it uses the Internet as knowledge source and (ii) it combines different extractions methods to improve the final result. In the experiments presented in this paper, NEBEL reached 65% accuracy in the English-Portuguese pair of languages.


bilingual lexicon never-ending machine learning natural language processing 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Carlson, A., Betteridge, J., Kisiel, B., Settles, B., Hruschka Jr, E.R., Mitchell, T.M.: Toward an architecture for never-ending language learning. In: Proceedings of the Twenty-Fourth Conference on Artificial Intelligence, AAAI 2010 (2010)Google Scholar
  2. 2.
    de Medeiros Caseli, H., da Paz Silva, A.M., das Graças Volpe Nunes, M.: Evaluation of methods for sentence and lexical alignment of brazilian portuguese and english parallel texts. In: Bazzan, A.L.C., Labidi, S. (eds.) SBIA 2004. LNCS (LNAI), vol. 3171, pp. 184–193. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  3. 3.
    Caseli, H.M., Nunes, M.G.V., Forcada, M.L.: Automatic induction of bilingual resources from aligned parallel corpora: application to shallow-transfer machine translation. Machine Translation 20(4), 227–245 (2006)CrossRefGoogle Scholar
  4. 4.
    Martins, D.B.d.J.: Pós-edição automática de textos traduzidos automaticamente de inglês para português do Brasil. Master’s thesis, Centro de Ciências Exatas e de Tecnologia – Programa de Pós-graduao em Ciência da Computação, Universidade de São Carlos (2014)Google Scholar
  5. 5.
    Mitchell, T.M., Betteridge, J., Carlson, A., Hong, S.A., Hruscka, E.A.L.M.E., Wang, S.: Never-ending language learning: The Readtheweb Manifesto (May 2008)Google Scholar
  6. 6.
    Och, F.J., Ney, H.: A systematic comparison of various statistical alignment models, vol. 29, pp. 19–51. Association for Computational Linguistics (2003)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Thiago Lima Vieira
    • 1
  • Helena de Medeiros Caseli
    • 1
  1. 1.Federal University of São CarlosSão CarlosBrazil

Personalised recommendations