Towards a corpus-based dictionary of German noun-verb collocations

We 1 describe our attempts to automatically extract raw material for a dictionary of German noun-verb collocations from large corpora of newspaper text. Such a dictionary should be about collocations and it should include a description of their linguistic properties, rather than listing the mere lexical cooccurrence. Since most statistical collocation nding tools do not provide other than lexical cooc-currence information, we rst use symbolic extraction tools, based on a regular grammar over part-of-speech tagged and lemmatized text, and we use statistical lters thereafter. We rst list the types of information which should be contained in a collocational dictionary for Natural Language Processing, then sketch our extraction methods and nally discuss and illustrate our initial results.