VISUAL REPRESENTATION OF NATURAL-LANGUAGE SCENE DESCRIPTIONS

Citation
E. Giunchiglia et al., VISUAL REPRESENTATION OF NATURAL-LANGUAGE SCENE DESCRIPTIONS, IEEE transactions on systems, man and cybernetics. Part B. Cybernetics, 26(4), 1996, pp. 575-589
Citations number
25
Categorie Soggetti
Controlo Theory & Cybernetics","Computer Science Cybernetics","Robotics & Automatic Control
ISSN journal
10834419
Volume
26
Issue
4
Year of publication
1996
Pages
575 - 589
Database
ISI
SICI code
1083-4419(1996)26:4<575:VRONSD>2.0.ZU;2-F
Abstract
We are mainly interested in the development of CAD systems for interio r design, An effective use of such systems relies to a large extent on the characteristics of their user interface, This paper describes NAL IG, a system able to ''understand'' and ''reason about'' high level de scriptions of spatial scenes, The user interacts with the system by us ing a natural language interface which, though very simple, is express ive enough to allow the description of complex configurations of objec ts, NALIG replies by drawing on the screen an image mirroring its own ''understanding'' of the scene described. The comprehension process ha s required the integration of different AI-techniques (e,g., natural l anguage understanding, spatial reasoning, default and common sense rea soning).