11 citations · 32 across the 8 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.LG2021★ 10 cited
Simple data balancing achieves competitive worst-group-accuracy
Badr Youbi Idrissi, Martin Arjovsky, Mohammad Pezeshki +1
We study the problem of learning classifiers that perform well across (known or unknown) groups of data. After observing that common worst-group-accuracy datasets suffer from subst…
cs.CL2021★ 1 cited
Masked Adversarial Generation for Neural Machine Translation
Badr Youbi Idrissi, Stéphane Clinchant
Attacking Neural Machine Translation models is an inherently combinatorial task on discrete sequences, solved with approximate heuristics. Most methods use the gradient to attack t…