Adversarial training has been shown effective at endowing the learned representations with
stronger generalization ability. However, it typically requires expensive computation to …

The success of bidirectional encoders using masked language models, such as BERT, on
numerous natural language processing tasks has prompted researchers to attempt to …

Neural machine translation models are often biased toward the limited translation
references seen during training. To amend this form of overfitting, in this paper we propose …

We propose a novel data-augmentation technique for neural machine translation based on
ROT-$ k $ ciphertexts. ROT-$ k $ is a simple letter substitution cipher that replaces a letter in …

Multiscale feature hierarchies have been witnessed the success in the computer vision area.
This further motivates researchers to design multiscale Transformer for natural language …

We introduce Bi-SimCut: a simple but effective training strategy to boost neural machine
translation (NMT) performance. It consists of two procedures: bidirectional pretraining and …

Attention-based neural machine translation (NMT) models selectively focus on specific
source positions to produce a translation, which brings significant improvements over pure …

Learning multiscale Transformer models has been evidenced as a viable approach to
augmenting machine translation systems. Prior research has primarily focused on treating …

We introduce EM-Network, a novel self-distillation approach that effectively leverages target
information for supervised sequence-to-sequence (seq2seq) learning. In contrast to …

Code search, which locates code snippets in large code repositories based on natural
language queries entered by developers, has become increasingly popular in the software …