# Adversarial Neural Machine Translation

arXiv: https://arxiv.org/abs/1704.06933 · HTML: https://mlsanity.com/paper/1704.06933/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Apr 2017.

## Built on by (most cited first, 21 of 21)

- [Quark: Controllable Text Generation with Reinforced Unlearning](https://mlsanity.com/paper/2205.13636/) (2022)
- [Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning](https://mlsanity.com/paper/1805.10627/) (2018)
- [Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks](https://mlsanity.com/paper/2103.06982/) (2021)
- [Sequence-Level Training for Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/2106.08122/) (2021)
- [A Review of Text Style Transfer using Deep Learning](https://mlsanity.com/paper/2109.15144/) (2021)
- [AgreeSum: Agreement-Oriented Multi-Document Summarization](https://mlsanity.com/paper/2106.02278/) (2021)
- [On the Effectiveness of Offline RL for Dialogue Response Generation](https://mlsanity.com/paper/2307.12425/) (2023)
- [Adaptive Bridge between Training and Inference for Dialogue](https://mlsanity.com/paper/2110.11560/) (2021)
- [Attention Forcing for Machine Translation](https://mlsanity.com/paper/2104.01264/) (2021)
- [Sometimes We Want Translationese](https://mlsanity.com/paper/2104.07623/) (2021)
- [Stock Broad-Index Trend Patterns Learning via Domain Knowledge Informed Generative Network](https://mlsanity.com/paper/2302.14164/) (2023)
- [Bridging Dialects: Translating Standard Bangla to Regional Variants Using Neural Models](https://mlsanity.com/paper/2501.05749/) (2025)
- [Adversarial Machine Learning in Text Analysis and Generation](https://mlsanity.com/paper/2101.08675/) (2021)
- [Reward Models are Metrics in a Trench Coat](https://mlsanity.com/paper/2510.03231/) (2025)
- [Symbolic integration by integrating learning models with different strengths and weaknesses](https://mlsanity.com/paper/2103.05497/) (2021)
- [Improvement in Machine Translation with Generative Adversarial Networks](https://mlsanity.com/paper/2111.15166/) (2021)
- [Exploiting Multilingualism in Low-resource Neural Machine Translation via Adversarial Learning](https://mlsanity.com/paper/2303.18011/) (2023)
- [Parallel Attention Forcing for Machine Translation](https://mlsanity.com/paper/2211.03237/) (2022)
- [A Sea-Land Clutter Classification Framework for Over-the-Horizon-Radar Based on Weighted Loss Semi-supervised GAN](https://mlsanity.com/paper/2305.04021/) (2023)
- [AST-MHSA : Code Summarization using Multi-Head Self-Attention](https://mlsanity.com/paper/2308.05646/) (2023)
- [High-Quality Data Augmentation for Low-Resource NMT: Combining a Translation Memory, a GAN Generator, and Filtering](https://mlsanity.com/paper/2408.12079/) (2024)

## Abstract (arXiv)

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 EnglishrightarrowFrench and GermanrightarrowEnglish translation tasks show that Adversarial-NMT can achieve significantly better translation quality than several strong baselines.