Descripción del proyecto
Enseñar a las máquinas a interactuar con las personas
Conversar es un ejercicio de comunicación interactiva entre dos o más personas; la interacción es individual y única. Las personas modifican el contenido y la forma de las enunciaciones según el interlocutor (estudiantes, familiares, compañeros y abuelos) y controlan su nivel de comprensión. En el campo de la informática y la inteligencia artificial (IA), los sistemas de procesamiento del lenguaje natural (PLN) posibilitan que las personas hablen con las máquinas. Con todo, los sistemas de PLN carecen de naturalidad en la interacción. En este contexto, el proyecto IDDISC, financiado con fondos comunitarios, favorecerá la interacción lingüística individualizada con sistemas informáticos. En concreto, se abordarán las diferencias individuales en la comprensión a nivel pragmático y discursivo. En el proyecto se desarrollarán modelos innovadores para predecir inferencias basadas en las propiedades cognitivas específicas de un individuo y su dominio de conocimiento.
Objetivo
Humans adapt the content and form of their utterances to different interlocutors (students vs. colleagues vs. granny), and monitor the level of understanding in their conversational partner. Today's NLP systems are however largely blind with respect to individual variation in language comprehension, which in turn leads to misunderstandings and lack of naturalness in the interaction.
The vision of IDDISC is to enable individualised language interaction with computer systems, such that information or explanations generated by a system will fit the user and the situation, by explicitly modelling their state of understanding. This project will break completely new ground by addressing individual differences in comprehension at the pragmatics and discourse level, i.e. with respect to the inferred meaning that goes beyond the literal meaning of an utterance.
This vision requires ground-breaking contributions at the intersection of individual differences research, language processing models and statistical methods: (a) we will develop innovative models that can predict inferences based on specific cognitive properties of an individual and their domain knowledge; (b) we will undertake foundational research on the factors that lead to individual differences in pragmatic inferences; (c) we will contribute to new statistical modelling techniques for quantifying similarities between individuals, as well as new methods for modelling inference variation in the NLP pipeline; (d) we will test the success of adaptation to individual characteristics in practical applications.
This project will make it possible to reduce the risk of misunderstandings, and enable adaptation of automatically generated language (e.g. explanations, summaries) to specific users. The new statistical methods and crowd-sourcing paradigms developed as part of this project will open the door to other researchers for investigating individual differences in all areas of language processing.
Ámbito científico
Programa(s)
Régimen de financiación
ERC-STG - Starting GrantInstitución de acogida
66123 Saarbrucken
Alemania