Intelligent System Demonstrations

Friday, 7 May 2010, 14:00-15:30

SETN-2010 will host demonstrations of state-of-the-art AI implementations, providing participants the opportunity to see research results in action and interact with the researchers.

Full descriptions will be included in the companion volume of the SETN proceedings.

The following demonstrations have been selected:

K. Pastra, P. Dimitrakis, E. Balta, and G. Karakatsiotis,
PRAXICON and its automatic population modules.

Abstract
The "semantic gap" between the low-level features of sensorimotor data and their meaning as expressed through language is one of the fundamental chal- lenges in developing intelligent systems. In this demonstration, we will present the very first release of the PRAXICON, a grounded concept world, in the form of a knowledge base tightly coupled with programs that perform a generative analysis of sensorimotor representations. This is the first grounding resource that is coupled with compositional and generative modules for visual and mo- toric representation analysis and the first one that integrates the output of such modules with language representations within and across concepts, taking into consideration the dynamic role of language within the semantic interplay with sensorimotor representations. We will also present three modules that extract information from three sources of structured, semi-structured and legacy data, for populating the PRAXICON: (a) the COSMOROE annotated audiovisual corpus of TV travel series, (b) the POETICON cognitive experiments corpus, and (c) WordNet.

Dimitrios Sklavakis and Ioannis Refanidis,
MATHESIS: A Web Based Intelligent Tutoring School for Algebra.

Abstract
The MATHESIS Intelligent Tutoring School for Algebra is an integrated web based environment for tutoring expansion and factoring of algebraic expressions. It provides full support for the management of the usual homework workflow: Student and teacher registration, creation and management of classes and test papers, individualized assignment of exercises, intelligent step by step guidance in solving exercises, student interaction recording, skill mastery statistics and student assessment. The intelligence of the system lies in the MATHESIS Algebra Tutor, a model-tracing tutor for expanding and factoring algebraic expressions. The tutor teaches a breadth of 16 top-level math skills: monomial multiplication, division and power, monomial-polynomial and polynomial-polynomial multiplication, parentheses elimination, collect like terms, identities (square of sum and difference, product of sum-difference, cube of sum and difference), factoring (common factor, term grouping, identities, trinomial). These skills are further decomposed in more simple ones giving a deep domain model of 104 math skills.

John Zakos and Liesl Capper,
MyCyberTwin: An Artificial Intelligence Platform for the Creation of Chat Robots

Abstract
This demonstation presents an artificial intelligence platform, MyCyberTwin, that allows users to create chat robots called CyberTwins. CyberTwins "live" on the web and autonomously chat to real people via various channels, engaging them in natural, humanized, accurate conversations across application areas that include customer support, sales, education through to entertainment. Traditionally, the creation of chat robots has been an exclusively technical task, requiring intimate knowledge of computer science principles and techniques. For the lay computer user, the MyCyberTwin platform provides a solution to this obstacle by making it easy and intuitive for any body to create a chat robot that has personality, knowledge and intelligence.

Vangelis Karkaletsis, Stasinos Konstantopoulos, Dimitris Bilidas, Athanasios Tegos, Ion Androutsopoulos, Gerasimos Lampouras, Prodromos Malakasiotis, Panos Trahanias, and Haris Baltzakis,
Natural Interaction with Personality and Dialogue Enabled Robots

Abstract
The subject of this demonstration is natural human-robot interaction. More specifically, we demonstrate technological advancements that enable robots to perceive and understand natural human behavior, as well as to act in ways that are familiar to humans. The demonstration is built around a museum guide use- case, where a simulated robotic guide operates in a virtual environment. During the demonstration, visitors are able to interact with the simulated robot using natural language and gestures. At the same time, videos of a real robot operating in a real museum are also demonstrated. Both the real and the simulated robot use the same software components.