Project description DEENESFRITPL Computational modelling for a deeper understanding of human language use Modelling the ability to communicate using language via computational methods is an exciting open problem. To tackle this challenge, the EU-funded DREAM project will create new computational models of dialogue agents that learn how to engage in conversation directly from data involving language use. The project combines ideas from linguistics with new developments in machine learning related to artificial neural network systems. This will enable dialogue agents to learn the representations that they manipulate directly from experience. The dialogue agents will learn from human conversations that have a task-oriented goal. The project will advance the development of complex conversational agents and improve scientific understanding of human language use. Show the project objective Hide the project objective Objective 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. Fields of science humanitieslanguages and literaturegeneral language studieshumanitieslanguages and literaturelinguisticsnatural sciencescomputer and information sciencesartificial intelligencecomputational intelligence Keywords dialogue modelling computational semantics and pragmatics Programme(s) H2020-EU.1.1. - EXCELLENT SCIENCE - European Research Council (ERC) Main Programme Topic(s) ERC-2018-COG - ERC Consolidator Grant Call for proposal ERC-2018-COG See other projects for this call Funding Scheme ERC-COG - Consolidator Grant Host institution UNIVERSITEIT VAN AMSTERDAM Net EU contribution € 2 000 000,00 Address SPUI 21 1012WX Amsterdam Netherlands See on map Region West-Nederland Noord-Holland Groot-Amsterdam Activity type Higher or Secondary Education Establishments Links Contact the organisation Opens in new window Website Opens in new window Participation in EU R&I programmes Opens in new window HORIZON collaboration network Opens in new window Total cost € 2 000 000,00 Beneficiaries (1) Sort alphabetically Sort by Net EU contribution Expand all Collapse all UNIVERSITEIT VAN AMSTERDAM Netherlands Net EU contribution € 2 000 000,00 Address SPUI 21 1012WX Amsterdam See on map Region West-Nederland Noord-Holland Groot-Amsterdam Activity type Higher or Secondary Education Establishments Links Contact the organisation Opens in new window Website Opens in new window Participation in EU R&I programmes Opens in new window HORIZON collaboration network Opens in new window Total cost € 2 000 000,00
