Multiobjective Genetic Programming for Natural Language Parsing and Tagging

  • L. Araujo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4193)


Parsing and Tagging are very important tasks in Natural Language Processing. Parsing amounts to searching the correct combination of grammatical rules among those compatible with a given sentence. Tagging amounts to labeling each word in a sentence with its lexical category and, because many words belong to more than one lexical class, it turns out to be a disambiguation task. Because parsing and tagging are related tasks, its simultaneous resolution can improve the results of both of them. This work aims developing a multiobjective genetic program to perform simultaneously statistical parsing and tagging. It combines the statistical data about grammar rules and about tag sequences to guide the search of the best structure. Results show that any of the implemented multiobjective optimization models improve on the results obtained in the resolution of each problem separately.


Multiobjective Optimization Parse Tree Syntactic Category Aggregative Function Grammar Rule 
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.
    Araujo, L.: Part-of-speech tagging with evolutionary algorithms. In: Gelbukh, A. (ed.) CICLing 2002. LNCS, vol. 2276, pp. 230–239. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  2. 2.
    Araujo, L.: Genetic programming for natural language parsing. In: Keijzer, M., O’Reilly, U.-M., Lucas, S.M., Costa, E., Soule, T. (eds.) EuroGP 2004. LNCS, vol. 3003, pp. 230–239. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  3. 3.
    Charniak, E.: Statistical Language Learning. MIT Press, Cambridge (1993)Google Scholar
  4. 4.
    Coello Coello, C.A., Van Veldhuizen, D.A., Lamont, G.B.: Evolutionary Algorithms for Solving Multi-Objective Problems. Kluwer Academic, Dordrecht (2002)MATHGoogle Scholar
  5. 5.
    Dalrymple, M.: How much can tagging help parsing? Technical report, Department of Computer Science, King’s College, London (2004)Google Scholar
  6. 6.
    Deb, K., Kalyanmoy, D.: Multi-Objective Optimization Using Evolutionary Algorithms. John Wiley & Sons, Chichester (2001)MATHGoogle Scholar
  7. 7.
    Deb, K., Pratab, A., Agarwal, S., Meyarivan, T.: A fast and elitist multiobjective genetic algorithm: Nsga-ii. IEEE transactions on Evolutionary Computations 6(2), 182–197 (2002)CrossRefGoogle Scholar
  8. 8.
    Fonseca, C.M., Fleming, P.J.: Genetic algorithms for multiobjective optimization: Formulation, discussion and generalization. In: Genetic Algorithms: Proc. of the Fifth Int. Conf., pp. 416–423. Morgan Kaufmann, San Francisco (1993)Google Scholar
  9. 9.
    Marcus, M.P., Santorini, B., Marcinkiewicz, M.A.: Building a large annotated corpus of english: The penn treebank. Computational Linguistics 19(2), 313–330 (1994)Google Scholar
  10. 10.
    Sampson, G.: English for the Computer. Clarendon Press, Oxford (1995)Google Scholar
  11. 11.
    Srinivas, N., Deb, K.: Multiobjective optimization using nondominated sorting in genetic algorithms. Evolutionary Computation 2(3), 221–248 (1994)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • L. Araujo
    • 1
  1. 1.Dpto. Sistemas Informáticos y ProgramaciónUniversidad Complutense de MadridSpain

Personalised recommendations