Descripción del proyecto
Modelización informática para lograr una comprensión más profunda del uso del lenguaje humano
Modelizar la capacidad de comunicarse con el lenguaje a través de métodos informáticos es un problema interesante aún sin respuesta. Para abordar este reto, el equipo del proyecto financiado con fondos europeos DREAM creará modelos informáticos innovadores de agentes conversacionales que puedan aprender a entablar una conversación directamente de datos sobre el uso del lenguaje. El proyecto combina ideas de la lingüística con nuevos desarrollos en el aprendizaje automático relacionados con sistemas de redes neuronales artificiales. Esto permitirá a los agentes conversacionales aprender directamente de la experiencia de las representaciones que manejan. Los agentes conversacionales aprenderán de conversaciones humanas que tienen un objetivo orientado a la tarea. El proyecto promoverá el desarrollo de agentes conversacionales complejos y mejorará la comprensión científica del uso del lenguaje humano.
Objetivo
Our ability to communicate using language in conversation is considered the hallmark of human intelligence. Yet, while holding a dialogue is effortless for most of us, modelling this basic human skill by computational means has proven extremely difficult. In DREAM, I address this challenge by establishing a new computational model of a dialogue agent that can learn to take part in conversation directly from data about language use. DREAM stands at the crossroads of the symbolic and the sub-symbolic traditions regarding the nature of human cognitive processing and, by extension, its computational modelling. My model is grounded in linguistic theories of dialogue, rooted in the symbolic tradition, but exploits recent advances in computational learning that allow the agent to learn the representations that it manipulates, which are distributed and sub-symbolic, directly from experience. This is an original approach that constitutes a paradigm shift in dialogue modelling --- from predefined symbolic representations to automatic representation learning --- that will break new scientific ground in Computational Linguistics, Linguistics, and Artificial Intelligence. The DREAM agent will be implemented as an artificial neural network system and trained with task-oriented conversations where the participants have a well-defined end goal. The agent will be able to integrate linguistic and perceptual information and will be endowed with the capability to dynamically track both speaker commitments and partner-specific conventions, leading to more human-like and effective communication. Besides providing a breakthrough in our capacity to build sophisticated conversational agents, DREAM will have substantial impact on our scientific understanding of human language use, thanks to its emphasis on theory-driven hypotheses and model analysis.
Ámbito científico
Palabras clave
Programa(s)
Régimen de financiación
ERC-COG - Consolidator GrantInstitución de acogida
1012WX Amsterdam
Países Bajos