Advertisement

Part-of-Speech Tagging of Portuguese Based on Variable Length Markov Chains

  • Fábio Natanael Kepler
  • Marcelo Finger
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3960)

Abstract

Tagging is the task of attributing to words in context in a text, their corresponding Part-of-Speech (PoS) class. In this work, we have employed Variable Length Markov Chains (VLMC) for tagging, in the hope of capturing long distance dependencies. We obtained one of the best PoS tagging of Portuguese, with a precision of 95.51%. More surprisingly, we did that with a total time of training and execution of less than 3 minutes for a corpus of almost 1 million words. However, long distance dependencies are not well captured by the VLMC tagger, and we investigate the reasons and limitations of the use of VLMCs. Future researches in statistical linguistics regarding long range dependencies should concentrate in other ways of solving this limitation.

Keywords

Execution Time Total Execution Time Training Corpus Distance Dependency Range Dependency 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Schütze, H., Singer, Y.: Part-of-speech tagging using a variable memory markov model. In: Proceedings of ACL 32nd (1994)Google Scholar
  2. 2.
    Bühlmann, P., Wyner, A.J.: Variable length markov chains. Annals of Statistics 27(2), 480–513 (1999)CrossRefGoogle Scholar
  3. 3.
    Mächler, M., Bühlmann, P.: Variable length markov chains: Methodology, computing and software. Research Report 104, Eidgenossische Technische Hochschule (ETH), CH-8091 Zürich, Switzerland, Seminar fur Statistik (2002)Google Scholar
  4. 4.
    Alves, C.D.C., Finger, M.: Etiquetagem do português clássico baseada em córpora. In: Proceedings of IV Encontro para o Processamento Computacional da Língua Portuguesa Escrita e Falada (PROPOR 1999), Évora, Portugal, pp. 21–22 (1999)Google Scholar
  5. 5.
    Aires, R.V.X.: Implementação, adaptação, combinação e avaliação de etiquetadores para o português do brasil. Dissertação de mestrado, Instituto de Ciências Matemáticas e Computação, Universidade de São Paulo - Campus São Carlos (2000)Google Scholar
  6. 6.
    Finger, M.: Técnicas de otimização da precisão empregadas no etiquetador Tycho Brahe. In: Proceedings of V Encontro para o Processamento Computacional da Língua Portuguesa Escrita e Falada (PROPOR 2000), Atibaia, Brazil, pp. 19–22 (2000)Google Scholar
  7. 7.
    IEL-UNICAMP and IME-USP: Corpus Anotado do Português Histórico Tycho Brahe (2005) Acessado em (2005)Google Scholar
  8. 8.
    Kepler, F.N.: Um etiquetador morfo-sintático baseado em cadeias de markov de tamanho variável. Dissertação de mestrado, Programa de Pós-Graduação em Ciência da Computação, Instituto de Matemática e Estatística, Universidade de São Paulo (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Fábio Natanael Kepler
    • 1
  • Marcelo Finger
    • 1
  1. 1.IME – Instituto de Matemática e EstatísticaUSP – Universidade de São PauloBrazil

Personalised recommendations