Computational mechanisms of teacher-pupil knowledge transfer
Teaching is one of the most complex and efficient forms for social learning, as it largely mitigates the costs of individual learning through the capitalization of others’ experiences. However, while recent efforts have shed consi...
ver más
¿Tienes un proyecto y buscas un partner? Gracias a nuestro motor inteligente podemos recomendarte los mejores socios y ponerte en contacto con ellos. Te lo explicamos en este video
Proyectos interesantes
TIN2014-57226-P
APRENDIZAJE COMPUTACIONAL Y COMUNICACION
90K€
Cerrado
WIKOLLECT
Workflows for the Large Scale Collection and Transference of...
183K€
Cerrado
CLOSER
Bringing Cognitive Linguistics and Language Teaching Closer...
214K€
Cerrado
LTfLL
Language Technology for Lifelong Learning
4M€
Cerrado
Fecha límite de participación
Sin fecha límite de participación.
Descripción del proyecto
Teaching is one of the most complex and efficient forms for social learning, as it largely mitigates the costs of individual learning through the capitalization of others’ experiences. However, while recent efforts have shed considerable light into how human learning is computationally modeled, very little is known about how human teaching can be computationally implemented in the context of goal-directed behaviours. COMPTEACH is an innovative research program conceived to bridge this gap by combining cutting-edge methods in cognitive science, experimental and social psychology, with state-of-the-art techniques from Reinforcement Learning (RL) and Natural Language Processing (NLP). It aims at understanding the computational makeup of pedagogical knowledge transfer between experienced learners (teachers) and novel naive learners (pupils). COMPTEACH will first identify actors’ choice strategies (as indexed by model parameters) and evaluate the extent to which pedagogical texts crafted by teachers and addressed to pupils lead to meaningful parameter correlations between the two. Secondly, the action will implementNLP tools to identify how the teachers' own computational strategies are encoded in the semantic and syntactic structures of pedagogical texts. Finally, the project will study how the teachers’ own learning process and metacognitive features affect knowledge transfer. By tackling teaching from a computational perspective without losing sight of its socio-cognitive underpinnings, COMPTEACH will produce a novel quantitative understanding of experience transfer, and establish novel bridges between teaching, cognitive science, social psychology and computational modeling. Future directions of this project will involve studying knowledge transfer in individuals afflicted by lasting underlying health conditions, and the development of ecological experiments to approach teacher-student and doctor-patient real-world interactions.