Project description
Teaching machines to interact with humans
Conversation is interactive communication between two or more people. The interaction is individual and unique. People modify content and form of utterances to different interlocutors (students, relatives, colleagues, grandparents) and monitor their level of understanding. In the field of computer science and AI, natural language processing (NLP) systems make it possible for humans to talk to machines. But NLP systems lack naturalness in the interaction. In this context, the EU-funded IDDISC project will enable individualised language interaction with computer systems. Specifically, it will address individual differences in comprehension at the pragmatics and discourse level. The project will develop innovative models to predict inferences based on specific cognitive properties of an individual and their domain knowledge.
Objective
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.
Fields of science
Programme(s)
Topic(s)
Funding Scheme
ERC-STG - Starting GrantHost institution
66123 Saarbrucken
Germany