However, we demonstrate that formalized fairness metrics and quantitative analysis on their own are insufficient for capturing the risk of representational harm in automatic cropping.
Pre-training models on vast quantities of unlabeled data has emerged as an effective approach to improving accuracy on many NLP tasks.
Ranked #1 on Machine Translation on WMT2016 Romanian-English (using extra training data)
Previous work on neural noisy channel modeling relied on latent variable models that incrementally process the source and target sentence.
This paper describes Facebook FAIR's submission to the WMT19 shared news translation task.
Ranked #1 on Machine Translation on WMT2019 English-German