Automatic extraction of subcategorization from corpora

  • Authors:
  • Ted Briscoe;John Carroll

  • Affiliations:
  • University of Cambridge, Cambridge, UK;University of Sussex, Brighton, UK

  • Venue:
  • ANLC '97 Proceedings of the fifth conference on Applied natural language processing
  • Year:
  • 1997

Quantified Score

Hi-index 0.00

Visualization

Abstract

We describe a novel technique and implemented system 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, on a sample of 14 verbs which exhibit multiple complementation patterns, demonstrates that the technique achieves accuracy comparable to previous approaches, which are all limited to a highly restricted set of subcategorization classes. We also demonstrate that a subcategorization dictionary built with the system improves the accuracy of a parser by an appreciable amount1.