Towards Robust Neural Machine Translation
arXiv:1805.06130
Abstract
Small perturbations in the input can severely distort intermediate representations and thus impact translation quality of neural machine translation (NMT) models. In this paper, we propose to improve the robustness of NMT models with adversarial stability training. The basic idea is to make both the encoder and decoder in NMT models robust against input perturbations by enabling them to behave similarly for the original input and its perturbed counterpart. Experimental results on Chinese-English, English-German and English-French translation tasks show that our approaches can not only achieve significant improvements over strong NMT systems but also improve the robustness of NMT models.
arXiv commentAccepted by ACL 2018
References in corpus (14)
- Sequence to Sequence Learning with Neural Networks
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Improving neural networks by preventing co-adaptation of feature detectors
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- Convolutional Sequence to Sequence Learning
- Improved Techniques for Training GANs
- Distributional Smoothing with Virtual Adversarial Training
- Professor Forcing: A New Algorithm for Training Recurrent Networks
- Neural Machine Translation in Linear Time
- Adversarial Learning for Neural Dialogue Generation
- A Teacher-Student Framework for Zero-Resource Neural Machine Translation
- Improving the Robustness of Deep Neural Networks via Stability Training
- Asynchronous Bidirectional Decoding for Neural Machine Translation
- Deep Neural Machine Translation with Linear Associative Unit
Cited by in corpus (12)
- Ancient-Modern Chinese Translation with a Large Training Dataset
- Improving the Robustness of Speech Translation
- A Reinforced Generation of Adversarial Examples for Neural Machine Translation
- Adversarial Training with Contrastive Learning in NLP
- Learning Shared Semantic Space for Speech-to-Text Translation
- Simple Contrastive Representation Adversarial Learning for NLP Tasks
- Automatic Testing and Improvement of Machine Translation
- Neural Machine Translation: A Review and Survey
- Syntax-Enhanced Neural Machine Translation with Syntax-Aware Word Representations
- Listening while Speaking and Visualizing: Improving ASR through Multimodal Chain
- Regularized Context Gates on Transformer for Machine Translation
- Dual Past and Future for Neural Machine Translation