Masao Yokota:
An Approach to Integrated Spatial Language
Understanding Based on Mental Image Directed Semantic Theory
Abstract
From the semantic viewpoint, spatial expressions have the virtue of relating
in some way to visual scenes being described. Therefore, their semantic descriptions
can be grounded in perceptual representations. The Mental Image Directed
Semantic Theory (MIDST) has proposed an omnisensual mental image model and
its description language Lmd. This language is employed
for many-sorted predicate logic and can provide spatial expressions with
computable semantic descriptions as their perceptual representations. This
paper presents a brief sketch of the MIDST, and focuses on word meaning description
and spatial language understanding in association with the mental image model
for human-robot dialogue facilitation.
|
