Using self-trained bilexical preferences to improve disambiguation accuracy
Gertjan van Noord · 2007
A method is described to incorporate bilexical preferences between phrase heads, such as selection restrictions, in a Maximum-Entropy parser for Dutch. The bilexical preferences are modelled as association rates which are determined on the basis of a very large parsed corpus (about 500M words). We show that the incorporation of such self-trained preferences improves parsing accuracy significantly.