Lithuanian dependency parsing with rich morphological features

Abstract

We present the first statistical dependency parsing results for Lithuanian, a morphologically rich language in the Baltic branch of the Indo-European family. Using a greedy transition-based parser, we obtain a labeled attachment score of 74.7 with gold morphology and 68.1 with predicted morphology (77.8 and 72.8 unlabeled). We investigate the usefulness of different features and find that rich morphological features improve parsing accuracy significantly, by 7.5 percentage points with gold features and 5.6 points with predicted features. As expected, CASE is the single most important morphological feature, but virtually all available features bring some improvement, especially under the gold condition