Robust Neural Machine Translation with Doubly Adversarial Inputs

This document discusses using adversarial training methods to improve neural machine translation. Specifically, it explores training a Transformer model with both original inputs and their "doubly adversarial" corrupted versions to learn robust representations. Evaluation on two translation tasks showed this approach improved BLEU scores over the baseline Transformer model, demonstrating the effectiveness of adversarial training for more robust neural machine translation.