Noun Phrase Recognition with Tree Patterns1

 András Hócza2

  Acta Cybernetica 16 (2004) 611-623.

Abstract:

 This paper offers a method for the noun phrase recognition of Hungarian natural language texts based on machine learning methods. The approach learns noun phrase tree patterns described by regular expressions from an annotated corpus. The tree patterns are completed with probability values using error statistics. The noun phrase recognition parser tries to find the best-fitting trees for a sentence using backtracking technique. The results are used in an information extraction toolchain.

Footnotes

 Patterns 1 Presented at the 1st Conference on Hungarian Computational Linguistics, December 10-11, 2003, Szeged.

 Hócza 2 University of Szeged, Department of Informatics, 6720 Szeged, Árpád tér 2. E-mail: hocza@inf.u-szeged.hu, Webpage: http://www.inf.u-szeged.hu