A CONNECTIONIST APPROACH TO PART-OF-SPEECH TAGGING

F. Zamora-Martínez, M. J. Castro-Bleda, S. España-Boquera, Salvador Tortajada, P. Aibar

Abstract

In this paper, we describe a novel approach to Part-Of-Speech tagging based on neural networks. Multilayer perceptrons are used following corpus-based learning from contextual and lexical information. The Penn Treebank corpus has been used for the training and evaluation of the tagging system. The results show that the connectionist approach is feasible and comparable with other approaches.

References

  1. Ahmed, Raju, S., Chandrasekhar, P., and Prasad, M. (2002). Application of multilayer perceptron network for tagging parts-of-speech. In Proc. Language Engineering Conference, pp. 57-63.
  2. Benello, J., Mackie, A., and Anderson, J. (1989). Syntactic category disambiguation with neural networks. Computer Speech and Language, 3:203-217.
  3. Brants, T. (2000). TnT: a statistical part-of-speech tagger. In Proc. 6th conference on Applied Natural Language Processing, pp. 224-231.
  4. Brill, E. (1995). Transformation-Based Error-Driven Learning and Natural Language Processing: A Case Study in Part-of-Speech Tagging. Computational Linguistics, 21(4):543-565.
  5. Charniak, E., Hendrickson, C., Jacobson, N., and Perkowitz, M. (1993). Equations for part-of-speech tagging. In Proc. National Conference on Artificial Intelligence, pp. 784-789.
  6. Daelemans, W., Zavrel, J., Berck, P., and Gillis, S. (1996). MBT: A Memory-Based Part-of-Speech Tagger Generator. In Proc. 4th Workshop on Very Large Corpora, pp. 14-27.
  7. Espan˜a, S., Zamora, F., Castro, M.-J., and Gorbe, J. (2007). Efficient BP Algorithms for General Feedforward Neural Networks. In vol. 4527 of LNCS, pp. 327-336. Springer.
  8. Gascó, G. and Sánchez, J. (2007). Part-of-speech tagging based on machine translation techniques. In Patt. Recog. and Image Anal., pp. 257-264.
  9. Giménez, J. and Márquez, L. (2004). SVMTool: A general pos tagger generator based on support vector machines. In Proc. 4th Conf. on LREC.
  10. Jurafsky, D. and Martin, J. H. (2000). Speech and Language Processing. Prentice Hall.
  11. Marcus, M. P., Santorini, B., and Marcinkiewicz, M. A. (1993). Building a large annotated corpus of English: The Penn Treebank. Computational Linguistics, 19(2):313-330.
  12. Marques, N. and Pereira, G. (2001). A POS-Tagger generator for Unknown Languages. Procesamiento del Lenguaje Natural, 27:199-207.
  13. Martín Valdivia, M. (2004). Algoritmo LVQ aplicado a tareas de Procesamiento del Lenguaje Natural. PhD thesis, Universidad de Málaga.
  14. Merialdo, B. (1994). Tagging English Text with a Probabilistic Model. Computational Linguistics, 20(2):155- 171.
  15. Pérez-Ortiz, J. and Forcada, M. (2001). Part-of-speech tagging with recurrent neural networks. In Proc. IJCNN, pp. 1588-1592.
  16. Pla, F. and Molina, A. (2004). Improving Part-of-Speech Tagging using Lexicalized HMMs. Natural Language Engineering, 10(2):167-189.
  17. Ratnaparkhi, A. (1996). A Maximum Entropy Part-OfSpeech Tagger. In Proc. 1st Conference on EMNLP, pp. 133-142.
  18. Rumelhart, D. E., Hinton, G. E., and Williams, R. J. (1986). Parallel distributed processing: explorations in the microstructure of cognition, chap. Learning internal representations by error propagation, pp. 318-362. MIT Press.
  19. Schmid, H. (1994). Part-of-Speech tagging with neural networks. In Proc. International COLING, pp. 172-176.
  20. Tortajada Velert, S., Castro Bleda, M. J., and Pla Santamaría, F. (2005). Part-of-Speech tagging based on artificial neural networks. In Proc. 2nd Language & Technology Conference, pp. 414-418.
  21. Voutilainen, A. (1999). Syntactic Wordclass Tagging, chapter Handcrafted rules, pp. 217-246. H. van Halteren.
  22. Zamora-Martínez, F., Castro-Bleda, M., and Espan˜aBoquera, S. (2009). Fast evaluation of connectionist language models. In vol. 4507 of LNCS, pp. 144-151. Springer.
Download


Paper Citation


in Harvard Style

Zamora-Martínez F., J. Castro-Bleda M., España-Boquera S., Tortajada S. and Aibar P. (2009). A CONNECTIONIST APPROACH TO PART-OF-SPEECH TAGGING . In Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009) ISBN 978-989-674-014-6, pages 421-426. DOI: 10.5220/0002313004210426


in Bibtex Style

@conference{icnc09,
author={F. Zamora-Martínez and M. J. Castro-Bleda and S. España-Boquera and Salvador Tortajada and P. Aibar},
title={A CONNECTIONIST APPROACH TO PART-OF-SPEECH TAGGING},
booktitle={Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009)},
year={2009},
pages={421-426},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002313004210426},
isbn={978-989-674-014-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009)
TI - A CONNECTIONIST APPROACH TO PART-OF-SPEECH TAGGING
SN - 978-989-674-014-6
AU - Zamora-Martínez F.
AU - J. Castro-Bleda M.
AU - España-Boquera S.
AU - Tortajada S.
AU - Aibar P.
PY - 2009
SP - 421
EP - 426
DO - 10.5220/0002313004210426