An Experiment on Learning Appropriate Selectional Restrictions from a Parsed Corpus

Abstract

We present a methodology to extract Selectional Restrictions at a variable level of abstraction from phrasally analyzed corpora. The method relays in the use of a wide-coverage noun taxonomy and a statistical measure of the co-occurrence of linguistic items. Some experimental results about the performance of the method are provided.

11 pages

References in corpus (1)

• On Learning More Appropriate Selectional Restrictions

Cited by in corpus (2)

• Acquiring Word-Meaning Mappings for Natural Language Interfaces
• On Learning More Appropriate Selectional Restrictions