Hallucinated translations can severely undermine and raise safety issues when machine
translation systems are deployed in the wild. Previous research on the topic focused on …

As NLP models achieved state-of-the-art performances over benchmarks and gained wide
applications, it has been increasingly important to ensure the safe deployment of these …

Neural machine translation (NMT) often suffers from the vulnerability to noisy perturbations
in the input. We propose an approach to improving the robustness of NMT models, which …

Neural sequence generation models are known to “hallucinate”, by producing outputs that
are unrelated to the source text. These hallucinations are potentially harmful, yet it remains …

The development of deep learning techniques has allowed Neural Machine Translation
(NMT) models to become extremely powerful, given sufficient training data and training time …

Natural Language Generation (NLG) has made great progress in recent years due to the
development of deep learning techniques such as pre-trained language models. This …

In this paper, we propose a new adversarial augmentation method for Neural Machine
Translation (NMT). The main idea is to minimize the vicinal risk over virtual sentences …

This paper presents TransRepair, a fully automatic approach for testing and repairing the
consistency of machine translation systems. TransRepair combines mutation with …

Exploiting large pretrained models for various NMT tasks have gained a lot of visibility
recently. In this work we study how BERT pretrained models could be exploited for …

Textual adversarial samples play important roles in multiple subfields of NLP research,
including security, evaluation, explainability, and data augmentation. However, most work …