We present a dependency conversion of five German test sets from five different genres. The dependency representation is made as similar as possible to the dependency representation of TiGer, one of the two big syntactic treebanks of German. The purpose of these test sets is to enable researchers to test dependency parsing models on several different data sets from different text genres. We discuss some easy to compute statistics to demonstrate the variation and differences in the test sets and provide some baseline experiments where we test the effect of additional lexical knowledge on the out-of-domain performance of two state-of-the-art dependency parsers. Finally, we demonstrate with three small experiments that text normalization may be an important step in the standard processing pipeline when applied in an out-of-domain setting.
展开▼
