Combining Statistical and Rule-Based Approaches to Morphological Tagging of Czech Texts
Open Access
- 1 June 2008
- journal article
- Published by Charles University in Prague, Karolinum Press in The Prague Bulletin of Mathematical Linguistics
- Vol. 89 (1), 23-40
- https://doi.org/10.2478/v10108-009-0002-x
Abstract
Combining Statistical and Rule-Based Approaches to Morphological Tagging of Czech Texts This article is an extract of the PhD thesis (Spoustová, 2007) and it extends the article (Spoustová et al., 2007). Several hybrid disambiguation methods are described which combine the strength of hand-written disambiguation rules and statistical taggers. Three different statistical taggers (HMM, Maximum-Entropy and Averaged Perceptron) and a large set of hand-written rules are used in a tagging experiment using Prague Dependency Treebank. The results of the hybrid system are better than any other method tried for Czech tagging so far.Keywords
This publication has 1 reference indexed in Scilit:
- The Linguistic Basis of a Rule-Based Tagger of CzechLecture Notes in Computer Science, 2000