Skip to main content

Portuguese corpus-based learning using ETL

Abstract

We present Entropy Guided Transformation Learning models for three Portuguese Language Processing tasks: Part-of-Speech Tagging, Noun Phrase Chunking and Named Entity Recognition. For Part-of-Speech Tagging, we separately use the Mac-Morpho Corpus and the Tycho Brahe Corpus. For Noun Phrase Chunking, we use the SNR-CLIC Corpus. For Named Entity Recognition, we separately use three corpora: HAREM, MiniHAREM and LearnNEC06.

For each one of the tasks, the ETL modeling phase is quick and simple. ETL only requires the training set and no handcrafted templates. ETL also simplifies the incorporation of new input features, such as capitalization information, which are sucessfully used in the ETL based systems. Using the ETL approach, we obtain state-of-the-art competitive performance in all six corpora-based tasks. These results indicate that ETL is a suitable approach for the construction of Portuguese corpus-based systems.

References

  1. R. V. X. Aires, S. M. Aluísio, D. C. S. Kuhn, M. L. B. Andreeta, O. N. Oliveira-Jr. Combining Classifiers to Improve Part of Speech Tagging: A Case Study for Brazilian Portuguese. InProceedings of IBERAMIASBIA, pages 227–236, 2000.

  2. S. M. Aluísio, J. M. Pelizzoni, A. R. Marchi, L. Oliveira, R. Manenti, V. Marquiafável. An Account of the Challenge of Tagging a Reference Corpus for Brazilian Portuguese. InProceedings of PROPOR, Faro, pages 110–117, 2003.

  3. E. Brill. Transformation-Based Error-Driven Learning and Natural Language Processing: A Case Study in Part-of-Speech Tagging.Comput. Linguistics. 21(4):543–565, 1995.

    Google Scholar 

  4. J. R. Curran, R. K. Wong. Formalisation of Transformation-based Learning. InProceedings of the ACSC, Canberra, Australia, pages 51–57, 2000.

  5. M. Finger. Técnicas de Otimização da Precisão Empregadas no Etiquetador Tycho Brahe. InProceedings of PROPOR, São Paulo, pages 141–154, 2000.

  6. Radu Florian. Named Entity Recognition as a House of Cards: Classifier Stacking. InProceedings of 4 th conference on Computational Natural Language Learning — CONLL, pages 175–178, 2002.

  7. M. C. Freitas, J. C. Duarte, C. N. dos Santos, R. L. Milidiú, R. P. Renteria, V. Quental. A Machine Learning Approach to the Identification of Appositives. InProceedings of Ibero-American AI Conference, Ribeirão Preto, 2006.

  8. M. C. Freitas, M. Garrao, C. Oliveira, C. N. dos Santos, M. Silveira. A anotação de um corpus para o aprendizado supervisionado de um modelo de SN. InProceedings of the III TIL / XXV Congresso da SBC, São Leopoldo, 2005.

  9. D. Jurafsky, J. H. Martin. Speech and Language Processing. Prentice Hall, 2000.

  10. F. N. Kepler, M. Finger. Comparing Two Markov Methods for Part-of-Speech Tagging of Portuguese. InProceedings of IBERAMIA-SBIA, Ribeirão Preto, pages 482–491, 2006.

  11. D. S. Leite, L. H. M. Rino. Combining Multiple Features for Automatic Text Summarization through Machine Learning. InProceedings of PROPOR, Aveiro, Portugal, pages 122–132, 2008.

  12. L. Mangu, E. Brill. Automatic Rule Acquisition for Spelling Correction. InProceedings of The Fourteenth ICML, São Francisco, pages 187–94, 1997.

  13. European Language Resources Association. http://catalog.elra.info/, Sept 24, 2008.

  14. Linguateca. www.linguateca.pt/, Sept 24, 2008.

  15. Linguistic Data Consortium. www.ldc.upenn.edu/, Sept 24, 2008.

  16. C. N. Aranha. Reconhecimento de entidades mencionadas em português.O Cortex e a sua participação no HAREM, Linguateca, Portugal, 2007.

  17. O. Ferrández, Z. Kozareva, A. Toral, R. Muñoz, A. Montoyo. Reconhecimento de entidades mencionadas em português,Tackling HAREM’s Portuguese Named Entity Recognition task with Spanish resources, Linguateca, Portugal, 2007.

  18. IEL-UNICAMP; IME-USP. Corpus Anotado do Português Histórico Tycho Brahe. http://www.ime. usp.br/tycho/corpus/, Jan 23, 2008.

  19. R. S. Martnez, J. P. Neto, D. Caseiro. Statistical Machine Translation of Broadcast News from Spanish to Portuguese. InProceedings of PROPOR, Aveiro, Portugal, pages 112–121, 2008.

  20. R. L. Milidiú, J. C. Duarte, R. Cavalcante. Machine learning algorithms for portuguese named entity recognition. InProceedings of Fourth Workshop in Information and Human Language Technology, Ribeirão Preto, 2006.

  21. R. L. Milidiú, C. N. dos Santos, J. C. Duarte. Phrase Chunking using Entropy Guided Transformation Learning. InProceedings of ACL2008, Columbus, Ohio, 2008.

  22. The Lacio Web Project. www.nilc.icmc.usp.br/ lacioweb/ferramentas.htm, Jan 23, 2008.

  23. G. Ngai, R. Florian. Transformation-Based Learning in the Fast Lane. InProceedings of North Americal ACL, pages 40–47, June 2001.

  24. J. R. Quinlan. C4.5: programs for machine learning. Morgan Kaufmann Publishers Inc., San Francisco, 1993.

    Google Scholar 

  25. L. Ramshaw, M. Marcus. Text Chunking Using Transformation-Based Learning. InProceedings of S. Armstrong, K. W. Church, P. Isabelle, S. Manzi, E. Tzoukermann, D. Yarowsky, editors,Natural Language Processing Using Very Large Corpora, Kluwer, 1999.

  26. E. F. T. K. Sang, S. Buchholz. Introduction to the CoNLL-2000 shared task: chunking. InProceedings of the 2 nd workshop on Learning language in logic and the 4th CONLL, Morristown, USA, pages 127–132, 2000.

  27. C. N. dos Santos, C. Oliveira. Constrained Atomic Term: Widening the Reach of Rule Templates in Transformation Based Learning.EPIA, Covilhã, Portugal, pages 622–633, 2005.

    Google Scholar 

  28. C. N. dos Santos, R. L. Milidiú, R. P. Rentera. Portuguese Part-of-Speech Tagging Using Entropy Guided Transformation Learning. InProceedings of PROPOR, Aveiro, Portugal, pages 143–152, 2008.

  29. D. Santos, N. Cardoso. Reconhecimento de entidades mencionadas em português. Linguateca, Portugal, 2007.

  30. L. Sarmento, A. Sofia, L. Cabral. REPENTINO — A Wide-Scope Gazetteer for Entity Recognition in Portuguese. InProceedings of 7th Workshop on Computational Processing of Written and Spoken Portuguese, Itatiaia, pages 31–40, 2006.

  31. J. Su, H. Zhang. A Fast Decision Tree Learning Algorithm. AAAI, University of New Brunswick, NB, Canadá, 2006.

    Google Scholar 

  32. M. Surdeanu, R. Johansson, A. Meyers, L. Màrquez, J. Nivre. The CoNLL 2008 Shared Task on Joint Parsing of Syntactic and Semantic Dependencies.CoNLL 2008. InProceedings of the Twelfth Conference on Computational Natural Language Learning, Coling 2008 Organizing Committee, Manchester, England, pages 159–177, 2008.

  33. T. K. Sang, F. Erik. Introduction to the CoNLL-2002 Shared Task: Language-Independent Named Entity Recognition. InProceedings of CoNLL-2002, Taipei, Taiwan, pages 155–158, 2002.

  34. T. K. Sang, F. Erik, F. De Meulder. Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition. In Walter Daelemans and Miles Osborne, editors, InProceedings of CoNLL-2003, Edmonton, Canada, pages 142–147, 2003.

Download references

Author information

Authors and Affiliations

Authors

Rights and permissions

Open Access This article is distributed under the terms of the Creative Commons Attribution 2.0 International License ( https://creativecommons.org/licenses/by/2.0 ), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Reprints and Permissions

About this article

Cite this article

Milidiú, R.L., dos Santos, C.N. & Duarte, J.C. Portuguese corpus-based learning using ETL. J Braz Comp Soc 14, 17–27 (2008). https://doi.org/10.1007/BF03192569

Download citation

  • Received:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF03192569

Keywords

  • Entropy Guided Transformation Learning
  • transformation-based learning
  • decision trees natural
  • language processing