Analyzing an Italian Treebank with State-of-the-Art Statistical Parsers

In this paper we report work in progress on the application of state-of-the art statistical parsing techniques to Italian. Our approach partially differs from previous efforts on other languages because our investigation plans to compare not only results with different parsing methods but also on two different treebanks. Moreover, we try to find information theoretic confirmation of the empirical difference of the experimental results. We hope that exploring the field along these two different dimensions can provide useful hints on the influence of language specificities vs. treebank idiosyncrasies