Getting More from Morphology in Multilingual Dependency Parsing

Matt Hohensee and Emily M. Bender
University of Washington


Abstract

We propose a linguistically motivated set of features to capture morphological agreement and add them to the MSTParser dependency parser. Compared to the built-in morphological feature set, ours is both much smaller and more accurate across a sample of 20 morphologically annotated treebanks. We find increases in accuracy of up to 5.3% absolute. While some of this results from the feature set capturing information unrelated to morphology,there is still significant improvement, up to 4.6% absolute, due to the agreement model.