Paper: Informed ways of improving data-driven dependency parsing for German

ACL ID C10-2129
Title Informed ways of improving data-driven dependency parsing for German
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2010
Authors

We investigate a series of targeted modifi- cations to a data-driven dependency parser of German and show that these can be highly effective even for a relatively well studied language like German if they are made on a (linguistically and methodolog- ically) informed basis and with a parser implementation that allows for fast and robust training and application. Mak- ing relatively small changes to a range of very different system components, we were able to increase labeled accuracy on a standard test set (from the CoNLL 2009 shared task), ignoring gold standard part- of-speech tags, from 87.64% to 89.40%. The study was conducted in less than five weeks and as a secondary project of all four authors. Effective modifications in- clude the quality and combination of auto- assigned morphosyn...