Universiteit van Amsterdam

Events

Institute for Logic, Language and Computation

Please note that this newsitem has been archived, and may contain outdated information or links.

10 September 2019, Computational Linguistics Seminar, Zeynep Akata

Speaker: Zeynep Akata (University of Amsterdam)
Title: Representing and Explaining Novel Concepts with Minimal Supervision
Date: Tuesday 10 September 2019
Time: 16:00
Location: ILLC Seminar Room F1.15, Science Park 107, Amsterdam

Clearly explaining a rationale for a classification decision to an end-user can be as important as the decision itself. Existing approaches for deep visual recognition are generally opaque and do not output any justification text; contemporary vision-language models can describe image content but fail to take into account class-discriminative image properties which justify visual predictions. In this talk, I will present my past and current work on Zero-Shot Learning, Vision and Language for Generative Modeling and Explainable Artificial Intelligence where we show (1) how to generalize image classification models to cases when no visual training data is available, (2) how to generate images and image features using detailed visual descriptions, and (3) how our models focus on discriminating properties of the visible object, jointly predict a class label, explain why/not the predicted label is chosen for the image.

For more information, see http://projects.illc.uva.nl/LaCo/CLS/.

Please note that this newsitem has been archived, and may contain outdated information or links.