Extraction of Type-Logical Supertags from the Spoken Dutch Corpus

The Spoken Dutch Corpus assigns 1 million of its 9 million total words a syn- tactic annotation in the form of dependency graphs. We will look at strategies for automatically extracting a lexicon of type-logical supertags from these dependency graphs and investigate how different levels of lexical detail affect the size of the resulting lexicon as well as the performance with respect to supertag disambiguation.