Using Multi-Agent Systems to Visualize Text Descriptions

Abstract

Usually people make a visual representation of what they read. This is a fact inherent to their nature. Many efforts have been done in the last years to try to find a direct method to translate a text wrote on a natural language to a graphical representation. Some solutions try to represent mainly a static scene with the objects appearing in the text, also there are few approaches that try to build an animation from the action described in text. But in any case all the approaches found on literature are not reciprocal approaches; that is, if the visual result is not satisfactory another text must be wrote in order to get a better one. Software Engineering and in particular Agent Oriented Software Engineering treat this kind of problematic using model driven techniques over different intermediates models. In this paper such kind of solution is proposed to get not only a visual model of the text wrote, but also to get an intermediate model that could be used to modify the visual model without modify the text and also to propose an alternative narration if necessary. In order to validate the visual model obtained, a previous multi-agent system has been adapted to provide a representation to be run on the Alice System.