Noun phrase recognition with tree patterns

Hócza, András: Noun phrase recognition with tree patterns. In: Acta cybernetica, (16) 4. pp. 611-623. (2004)

Cikk, tanulmány, mű

Download (214kB) | Preview


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.

Item Type: Article
Journal or Publication Title: Acta cybernetica
Date: 2004
Volume: 16
Number: 4
ISSN: 0324-721X
Page Range: pp. 611-623
Language: angol
Event Title: Conference on Hungarian Computational Linguistics, 1., 2003, Szeged
Related URLs:
Uncontrolled Keywords: Természettudomány, Informatika, Nyelvtudomány
Additional Information: Bibliogr.: p. 622-623.; Abstract
Date Deposited: 2016. Oct. 15. 12:25
Last Modified: 2021. Mar. 24. 14:43

Actions (login required)

View Item View Item