Chapter

Connectionist, Statistical and Symbolic Approaches to Learning for Natural Language Processing

Volume 1040 of the series Lecture Notes in Computer Science pp 261-274

Date:

Implications of an automatic lexical acquisition system

  • Peter M. HastingsAffiliated withArtificial Intelligence Lab, The University of Michigan

* Final gross prices may vary according to local VAT.

Get Access

Abstract

Camille, the Contextual Acquisition Mechanism for Incremental Lexeme LEarning, was implemented as an addition to Lytinen's LINK parser for use in an information extraction task, automatically inferring the meanings of unknown words from context. Unlike many previous lexical acquisition systems, Camille was thoroughly tested within a complex, real-world domain. The implementation of this system produced many lessons which are applicable to language learning in general. This paper describes Camille's implications for evaluation, for knowledge representation, and for cognitive modeling.