tailieunhanh - Báo cáo khoa học: "LEARNING PERCEPTUALLY-GROUNDED THE PROJECT SEMANTICS"

Learning to Associate Scenes with Spatial Terms portrayed in the scene. It is to learn to associate all applicable terms to novel scenes. The T R is restricted to be a single point for the time being; current work is directed at addressing the more general case of an arbitrarily shaped TR. Another aspect of the task is that learning must take place in the absence of explicit negative instances. This condition is imposed so that the conditions under which learning takes place will be similar in this respect to those under which children learn. Given this, there are two. | LEARNING PERCEPTUALLY-GROUNDED SEMANTICS IN THE Lo PROJECT Terry Regier International Computer Science Institute 1947 Center Street Berkeley CA 94704 415 642-4274 X 184 regier@cogsci. Berkeley. ED u TR LM Above Figure 1 Learning to Associate Scenes with Spatial Terms ABSTRACT A method is presented for acquiring perceptually-grounded semantics for spatial terms in a simple visual domain as a part of the Lq miniature language acquisition 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 evidence. Solutions to these two problems are presented and the results discussed. 1 Introduction The Lũ language learning project at the International Computer Science Institute Feldman et al. 1990 Weber and Stolcke 1990 seeks to provide an account of language acquisition in the semantic domain of spatial relations between geometrical objects. Within this domain the work reported here addresses the subtask of learning to associate scenes containing several simple objects with terms to describe the spatial relations among the objects in the scenes. This is illustrated in Figure 1. For each scene the learning system is supplied with an indication of which object is the reference object we call this object the landmark or LM and which object is the one being located relative to the reference object this is the trajector or TR . The system is also supplied with a single spatial term that describes the spatial relation Supported through the International Computer Science Institute. portrayed in the scene. It is to learn to associate all applicable terms to novel scenes. The TR is restricted to be a single point for the time being current work is directed at addressing the more general case of an arbitrarily shaped TR. Another aspect of the task is that learning must take place in the absence of explicit negative instances. This .