Automatic Extraction of Subcategorization from Corpora – Ted Briscoe (University of Cambridge)

March 12, 1996 all-day

I will describe a novel technique for constructing a subcategorization dictionary from textual corpora. Each dictionary entry encodes the relative frequency of occurrence of a comprehensive set of subcategorization classes for English. An initial experiment demonstrates that the technique achieves accuracy comparable to previous approaches, which are all limited to a highly restricted set of subcategorization classes.

Center for Language and Speech Processing