Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations

1 code implementation • 8 Dec 2022 • Björn Plüster, Jakob Ambsdorf, Lukas Braach, Jae Hee Lee, Stefan Wermter

Natural language explanations promise to offer intuitively understandable explanations of a neural network's decision process in complex vision-language tasks, as pursued in recent VL-NLE models.

Explanation Generation Visual Entailment +1