Advertisement

Assigning Deep Lexical Types

  • João Silva
  • António Branco
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7499)

Abstract

Deep linguistic grammars provide complex grammatical representations of sentences, capturing, for instance, long-distance dependencies and returning semantic representations, making them suitable for advanced natural language processing. However, they lack robustness in that they do not gracefully handle words missing from the lexicon of the grammar. Several approaches have been taken to handle this problem, one of which consists in pre-annotating the input to the grammar with shallow processing machine-learning tools. This is usually done to speed-up parsing (supertagging) but it can also be used as a way of handling unknown words in the input. These pre-processing tools, however, must be able to cope with the vast tagset required by a deep grammar. We investigate the training and evaluation of several supertaggers for a deep linguistic processing grammar and report on it in this paper.

Keywords

supertagging deep grammar 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Mitkov, R. (ed.): The Oxford Handbook of Computational Linguistics. Oxford University Press (2004)Google Scholar
  2. 2.
    Manning, C., Schütze, H.: Foundations of Statistical Natural Language Processing, 1st edn. MIT Press (1999)Google Scholar
  3. 3.
    Bangalore, S., Joshi, A.: Disambiguation of super parts of speech (or supertags): Almost parsing. In: Proceedings of the 15th Conference on Computational Linguistics (COLING), pp. 154–160 (1994)Google Scholar
  4. 4.
    Joshi, A., Schabes, Y.: Handbook of Formal Languages and Automata. In: Tree-Adjoining Grammars. Springer (1996)Google Scholar
  5. 5.
    Bangalore, S., Joshi, A.: Supertagging: An approach to almost parsing. Computational Linguistics 25(2), 237–265 (1999)Google Scholar
  6. 6.
    Clark, S., Curran, J.: Log-linear models for wide-coverage CCG parsing. In: Proceedings of the 8th Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 97–104 (2003)Google Scholar
  7. 7.
    Clark, S., Curran, J.: The importance of supertagging for wide-coverage CCG parsing. In: Proceedings of the 20th Conference on Computational Linguistics (COLING), pp. 282–288 (2004)Google Scholar
  8. 8.
    Clark, S., Curran, J.: Wide-coverage efficient statistical parsing with CCG and log-linear models. Computational Linguistics 33, 493–552 (2007)zbMATHCrossRefGoogle Scholar
  9. 9.
    Prins, R., van Noord, G.: Reinforcing parser preferences through tagging. Traitment Automatique des Langues 44, 121–139 (2003)Google Scholar
  10. 10.
    Matsuzaki, T., Miyao, Y., Tsujii, J.: Efficient HPSG parsing with supertagging and CFG-filtering. In: Proceedings of the 20th International Joint Conference on Artificial Intelligence (IJCAI), pp. 1671–1676 (2007)Google Scholar
  11. 11.
    Blunsom, P.: Structured Classification for Multilingual Natural Language Processing. Ph.D. thesis, University of Melbourne (2007)Google Scholar
  12. 12.
    Dridan, R.: Using Lexical Statistics to Improve HPSG Parsing. Ph.D. thesis, University of Saarland (2009)Google Scholar
  13. 13.
    Brants, T.: TnT — a statistical part-of-speech tagger. In: Proceedings of the 6th Applied Natural Language Processing Conference and the 1st North American Chapter of the Association for Computational Linguistics, pp. 224–231 (2000)Google Scholar
  14. 14.
    Branco, A., Costa, F.: A computational grammar for deep linguistic processing of Portuguese: LX-Gram, version A.4.1. Technical Report DI-FCUL-TR-08-17, University of Lisbon (2008)Google Scholar
  15. 15.
    Costa, F., Branco, A.: LXGram: A Deep Linguistic Processing Grammar for Portuguese. In: Pardo, T.A.S., Branco, A., Klautau, A., Vieira, R., de Lima, V.L.S. (eds.) PROPOR 2010. LNCS (LNAI), vol. 6001, pp. 86–89. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  16. 16.
    Banko, M., Brill, E.: Mitigating the paucity of data problem: Exploring the effect of training corpus size on classifier performance for NLP. In: Proceedings of the 1st Human Language Technology (HLT) Conference (2001)Google Scholar
  17. 17.
    Banko, M., Brill, E.: Scaling to very very large corpora for natural language disambiguation. In: Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics and 10th Conference of the European Chapter of the Association for Computational Linguistics, pp. 26–33 (2001)Google Scholar
  18. 18.
    Giménez, J., Màrquez, L.: SVMTool: A general POS tagger generator based on support vector machines. In: Proceedings of the 4th Language Resources and Evaluation Conference (LREC) (2004)Google Scholar
  19. 19.
    Giménez, J., Màrquez, L.: SVMTool: Technical Manual v1.3. TALP Research Center, LSI Department, Universitat Politecnica de Catalunya (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • João Silva
    • 1
  • António Branco
    • 1
  1. 1.Departamento de Informática, Edifício C6, Faculdade de CiênciasUniversity of LisbonLisboaPortugal

Personalised recommendations