tech,16-2-P03-1009,bq We describe a new approach which involves clustering <term> subcategorization frame ( SCF ) </term> distributions using the <term> Information Bottleneck </term> and <term> nearest neighbour </term> methods .
tech,2-4-P03-1009,bq A novel <term> evaluation scheme </term> is proposed which accounts for the effect of <term> polysemy </term> on the <term> clusters </term> , offering us a good insight into the potential and limitations of <term> semantically classifying </term><term> undisambiguated SCF data </term> .
hide detail