Adversarial Neural Machine Translation

Abstract

In this paper, we study a new learning paradigm for Neural Machine Translation (NMT). Instead of maximizing the likelihood of the human translation as in previous works, we minimize the distinction between human translation and the translation given by an NMT model. To achieve this goal, inspired by the recent success of generative adversarial networks (GANs), we employ an adversarial training architecture and name it as Adversarial-NMT. In Adversarial-NMT, the training of the NMT model is assisted by an adversary, which is an elaborately designed Convolutional Neural Network (CNN). The goal of the adversary is to differentiate the translation result generated by the NMT model from that by human. The goal of the NMT model is to produce high quality translations so as to cheat the adversary. A policy gradient method is leveraged to co-train the NMT model and the adversary. Experimental results on English$\to$French and German$\to$English translation tasks show that Adversarial-NMT can achieve significantly better translation quality than several strong baselines.

ACML 2018

References in corpus (9)

• Sequence to Sequence Learning with Neural Networks
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Convolutional Neural Network Architectures for Matching Natural Language Sentences
• Dual Learning for Machine Translation
• Professor Forcing: A New Algorithm for Training Recurrent Networks
• An Actor-Critic Algorithm for Sequence Prediction
• Adversarial Learning for Neural Dialogue Generation
• The Optimal Reward Baseline for Gradient-Based Reinforcement Learning
• Neural Machine Translation with Reconstruction

Cited by in corpus (13)

• Language Generation with Recurrent Generative Adversarial Networks without Pre-training
• Actor-Critic based Training Framework for Abstractive Summarization
• A Study of Reinforcement Learning for Neural Machine Translation
• Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets
• Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation
• On the Weaknesses of Reinforcement Learning for Neural Machine Translation
• Neural Machine Translation with Adequacy-Oriented Learning
• Image Captioning Based on a Hierarchical Attention Mechanism and Policy Gradient Optimization
• Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter
• Greedy Search with Probabilistic N-gram Matching for Neural Machine Translation
• Boosting Naturalness of Language in Task-oriented Dialogues via Adversarial Training
• Neural Machine Translation: A Review and Survey
• Neural Sequence Model Training via $\alpha$-divergence Minimization