We present a novel methodology for building highly integrated multimodal systems. Our approach is motivated by neurological and behavioral theories of sensory perception in humans...
(LP)2 is a covering algorithm for adaptive Information Extraction from text (IE). It induces symbolic rules that insert SGML tags into texts by learning from examples found in a u...
The aim of our research is to build a Reflexive Agent, that is able to either manifest an emotion it is feeling or to hide it. If the Agent decides to manifest its emotion, it can...
Berardina De Carolis, Catherine Pelachaud, Isabell...
The ability to generate effective evaluative arguments is critical for systems intended to advise and persuade their users. We have developed a system that generates evaluative ar...
The progressive processing model allows a system to trade off resource consumption against the quality of the outcome by mapping each activity to a graph of potential solution met...
Story generation is experiencing a revival, despite disappointing preliminary results from the preceding three decades. One of the principle reasons for previous inadequacies was ...
Software design is the hardest part of creating intelligent agents. Therefore agent architectures should be optimized as design tools. This paper presents an architectural synthes...
R-max is a very simple model-based reinforcement learning algorithm which can attain near-optimal average reward in polynomial time. In R-max, the agent always maintains a complet...