Initial Explorations in Two-phase Turkish Dependency Parsing by Incorporating Constituents
İlknur Durgar El-Kahlout, Ahmet Afşın Akın, Ertugrul Yilmaz · 2014
This paper describes a two-phase Turkish dependency parsing which separates dependency and labeling into two similar to (McDonald et al., 2006b). First, in order to solve the lon g distance de- pendency attachment problem, the sentences are split into constituents and the dependencies are estimated on shorter sentences. Later, for better estimation of labels, Conditio nal Random Fields (CRFs) are used with previously learned chunk and several dependency and morphosyntactic features. Finally, a post-processing step is applied to correct some of la bels, if necessary.