News and Events: Open Positions

Please note that this newsitem has been archived, and may contain outdated information or links.

2 PhD positions on Visual Dialogue Models, Trento (Italy)

Deadline: Monday 16 May 2022

At the University of Trento, we are opening 2 PhD positions, one at the Computer Science Department (DISI) and the other at the Center for Mind/Brain Sciences (CIMeC), to run projects on Visual Dialogue Models. At least one of the two projects will be run in collaboration with Amazon Alexa (in Berlin) and focus on Adaptive Multimodal conversational agents.The call for the position at DISI will close on May 16th. The one at CIMeC will open soon.

Adaptive Multimodal conversational agents.

Thanks to the research on multi-task learning and on transferability, the current trend in natural language understanding is to build universal models: models pre-trained on several tasks and fine-tuned on a downstream task to which the acquired conceptual knowledge and skills are transferred. These steps are very important contributions to AI, and in particular to the development of conversational systems, but universal models do not model human intelligence diversity. We believe it is important to work with conversational models which have different prior experiences and use different conversational strategies. With the progress on modelling vision and language interaction, current dialogue models are able to deal with visually grounded language. However, they are not able to adapt their language use to the interlocutor, hence they miss an essential ability to be engaged in effective communication. ADAPT aims to address this problem.

To accomplish our overall goal, the research agenda of ADAPT capitalises on recent advances in the development of multimodal models; on the availability of multimodal datasets for referential visual games with textual interactions among players; and on methods developed recently within the research on emergent communication in referential games. To these active and promising fields, we will add a fundamental missing component, namely the view about how humans take community mutual knowledge into account and manage to adapt to each other through conversations.

The scholarship is supported by Amazon Alexa and the work will be run in collaboration with their research group.

For more information, see or contact Raffaella Bernardi at .

Please note that this newsitem has been archived, and may contain outdated information or links.