Descrizione del progetto
Insegnare alle macchine a interagire con gli esseri umani
Una conversazione consiste in una comunicazione interattiva tra due o più persone, con un’interazione individuale e unica. Le persone modificano il contenuto e la forma delle espressioni in base a diversi interlocutori (studenti, parenti, colleghi, nonni) e ne monitorano il livello di comprensione. Nel campo dell’informatica e dell’intelligenza artificiale, i sistemi di elaborazione del linguaggio naturale rendono possibile lo scambio orale tra esseri umani e macchine. Tuttavia, questi sistemi sono privi di naturalezza nell’interazione. In questo contesto, il progetto IDDISC, finanziato dall’UE, consentirà un’interazione linguistica individualizzata con i sistemi informatici. Nello specifico, affronterà le differenze individuali nella comprensione a livello pragmatico e di discorso. Il progetto svilupperà modelli innovativi per prevedere le inferenze sulla base delle specifiche proprietà cognitive di un individuo e della relativa conoscenza del settore.
Obiettivo
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.
Campo scientifico
Programma(i)
Argomento(i)
Meccanismo di finanziamento
ERC-STG - Starting GrantIstituzione ospitante
66123 Saarbrucken
Germania