NLP use of multiple sources of information available in a Spanish machine-readable dictionary

• Autores: Marisa Jiménez
• Localización: Proceedings of the Tenth EURALEX International Congress, EURALEX 2002: Copenhagen, Denmark, August 13-17, 2002 / Anna Braasch (ed. lit.), Claus Povlsen (ed. lit.), Vol. 1, 2003, ISBN 87-90708-09-1, págs. 129-135
• Idioma: inglés
• Enlaces
  • Texto completo (pdf)
• Resumen

  • This paper discusses how multiple sources of information available in a Spanish machine-readable dictionary (MRD) have provided valuable linguistic information to our Spanish NLP system. In particular we discuss how we have used the definitions, codes and headwords of the MRD to obtain morphological and semantic information, which is used by the Spanish morphology and generation modules in our system. In the first part of the paper we describe the mapping process of morphological information contained in the MRD codes, definitions, and headwords into the inflectional paradigms used by our Spanish morphological analyzer. In the second part we discuss how we used the MRD definitions to create links between Spanish noun/verb pairs; these links are used by our Spanish generation component.