2 papers
cs.LG2021
GuideBP: Guiding Backpropagation Through Weaker Pathways of Parallel Logits
Bodhisatwa Mandal, Swarnendu Ghosh, Teresa Gonçalves +3
Convolutional neural networks often generate multiple logits and use simple techniques like addition or averaging for loss computation. But this allows gradients to be distributed…
cs.CL2019
From Textual Information Sources to Linked Data in the Agatha Project
Paulo Quaresma, Vitor Beires Nogueira, Kashyap Raiyani +2
Automatic reasoning about textual information is a challenging task in modern Natural Language Processing (NLP) systems. In this work we describe our proposal for representing and…