Answers are grounded in this paper and cite their sources.
Several hybrid disambiguation methods are described which combine the strength of hand-written disambiguation rules and statistical taggers. Three different statistical (HMM, Maximum-Entropy and Averaged Perceptron) taggers are used in a tagging experiment using Prague Dependency Tree-bank. The results of the hybrid systems are better than any other method tried for Czech tagging so far.
No takes yet. Share an insight, caveat, or question.
Spoustová et al. (2007) studied this question.