01 / Expert
Scientific depth
Explains concepts with accuracy and context, using the learner's target language.
CHIST-ERA 2025 · Science in your own language
Science conversations in your own, everyday language.
The project
ARTICULATE brings together machine translation, conversational AI and speech technology to make scientific knowledge accessible beyond academia and English-speaking audiences.
We translate not only across languages, but across styles: from the formal language of science into everyday, engaging dialogue that learners can listen to, question and shape.
Research approach
ARTICULATE supports self-regulated learning through a pair of role-based conversational agents, grounded in translated scientific documents and responsive to each learner's language profile.
01 / Expert
Explains concepts with accuracy and context, using the learner's target language.
02 / Peer
Asks the questions that make difficult ideas approachable, using dialect and informal style.
03 / Learner
Listens, interjects and co-creates understanding through questions, remarks and ideas.
Objectives
Consortium
How can AI help people encounter science in a voice and language that feels like their own?
Edinburgh, United Kingdom
Dublin, Ireland
Oulu, Finland
People
Meet the researchers collaborating across language technology, learning sciences and human-centred AI.
Heriot-Watt University
Research Associate, School of Mathematical and Computer Sciences.
University College Dublin
Assistant Professor, School of Information and Communication Studies.
University of Oulu
Visiting Research Fellow, Learning and Educational Technology Research Lab.
University of Oulu
Professor of Learning and Educational Technology; Head of the LET Lab.
Research outputs
ARTICULATE publications, preprints and project materials will be collected here as they become available.
Funding
ARTICULATE is jointly funded by the Engineering and Physical Sciences Research Council (EPSRC), the Irish Research Council (IRC), and the Research Council of Finland through the CHIST-ERA consortium.
CHIST-ERA-25-SOL-01 · UKRI3908