Raffaella Bernardi: An old Artificial Intelligence dream that comes true: Merging language and vision modalities

In the last decade, there has been an explosion of papers on the combination of the language and vision modalities.  In this tutorial, we will first aim to understand why this is happening, what has made the investigation possible, and where do we stand now. We will see that research has been mostly been driven by applications, but that behind this work there are quite interesting foundational questions. We will conclude the tutorial by zooming into the issue of grounding and reference that has been in the discussion of Artificial Intelligence, and in particular of Computational Linguistics, since its start. Click here to read the presentation slides.

Biography

Raffaella Bernardi is an Assistant Professor at the University of Trento, Italy. She started her research career in 1997, and has been involved in both theoretical and applied AI research projects. Bernardi has mainly focussed on Language and Vision, Natural Language Syntax-Semantics Interface and Natural Language Interface to Information Systems. She is a member of the Cost Action The European Network on Integrating Vision and Language, and the coordinator of the Language-Vision area in the Language, Interaction and Computation Laboratory (CLIC) at the University of Trento. For more information about Raffaella Bernardi please click here.