Paper: Learning Perceptually-Grounded Semantics In The Lo Project

ACL ID P91-1018
Title Learning Perceptually-Grounded Semantics In The Lo Project
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 1991
Authors
  • Terry Regier (University of California at Berkeley, Berkeley CA)

A method is presented for acquiring perceptually- grounded semantics for spatial terms in a simple visual domain, as a part of the L0 miniature language acquisi- tion project. Two central problems in this learning task are (a) ensuring that the terms learned generalize well, so that they can be accurately applied to new scenes, and (b) learning in the absence of explicit negative ev- idence. Solutions to these two problems are presented, and the results discussed.