Discovery procedures for sublanguage selectional patterns: initial experiments

Abstract

This paper describes a semi-automated procedure for collecting the co-occurrence patterns from a sample of texts in a domain, and then using these patterns as the basis for selectional constraints in analyzing further texts. We discuss some of the difficulties in automating the collection process, and describe two experiments that measure the completeness of these patterns and their effectiveness compared with manually-prepared patterns. We then describe and evaluate a procedure for selectional constraint relaxation, intended to compensate for gaps in the set of patterns. Finally, we suggest how these procedures could be combined with a system that queries a domain expert, in order to produce a more efficient discovery procedure