Resumen de Learning through embodied conversational agents with semantic memory
P. Garrido, F. J. Martinez, Julio Barrachina Peris, S. Baldassarri, E. Cerezo, Francisco José Serón Arbeloa
Embodied Conversational Agents (ECAs) are interactive characters that exhibit human-like qualities, such as facialexpressions, lip-synch, or emotional voice, and are able to communicate with humans, or with other ECAs by using naturalhuman capabilities (speech, gestures, etc.). However, to make current ECAs’ dialogue management strategies moreappealing and real to the user, they should be aware of general knowledge about the external world. This factualknowledge, which is independent of personal experience, should be stored in their semantic memory. This paper presents aknowledge-based solution to improve learning through ECAs with factual knowledge based on semantics. In particular,we build this semantic memory bymeans of a novel proposal known as Daira. Moreover, we integrated Daira with Maxine,a powerful animation engine for developing applications with embodied animated agents. To illustrate the potential of ourapproach, we designed a proof of concept in which our system is able to provide data from the online Great AragoneseEncyclopedia (GEA),writtenin Spanish, to engage students.Theexperiments performed show the feasibilityandefficiencyof our proposal. In particular, we demonstrated that using enriched ECAS when searching information can enhancelearning motivation and learning performance, making the interaction process much more accurate, simpler, and near tothe students.
