# Dual Learning for Machine Translation

arXiv: https://arxiv.org/abs/1611.00179 · HTML: https://mlsanity.com/paper/1611.00179/

## Key facts

- Cited by 148 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Nov 2016.

## Built on by (most cited first, 30 of 148)

- [BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models](https://mlsanity.com/paper/2205.07680/) (2022)
- [Unsupervised Speech Recognition](https://mlsanity.com/paper/2105.11084/) (2021)
- [Neural Machine Translation for Low-Resource Languages: A Survey](https://mlsanity.com/paper/2106.15115/) (2021)
- [Generative Cooperative Learning for Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2203.03962/) (2022)
- [Survey of Low-Resource Machine Translation](https://mlsanity.com/paper/2109.00486/) (2021)
- [Exploring Dual-task Correlation for Pose Guided Person Image Generation](https://mlsanity.com/paper/2203.02910/) (2022)
- [Neural Machine Translation with Monolingual Translation Memory](https://mlsanity.com/paper/2105.11269/) (2021)
- [Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR](https://mlsanity.com/paper/2508.14029/) (2025)
- [Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigation](https://mlsanity.com/paper/2203.16586/) (2022)
- [Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks](https://mlsanity.com/paper/2107.01431/) (2021)
- [Bootstrapped Transformer for Offline Reinforcement Learning](https://mlsanity.com/paper/2206.08569/) (2022)
- [Civil Rephrases Of Toxic Texts With Self-Supervised Transformers](https://mlsanity.com/paper/2102.05456/) (2021)
- [Survey on reinforcement learning for language processing](https://mlsanity.com/paper/2104.05565/) (2021)
- [Controllable Generation from Pre-trained Language Models via Inverse Prompting](https://mlsanity.com/paper/2103.10685/) (2021)
- [Gradual Domain Adaptation without Indexed Intermediate Domains](https://mlsanity.com/paper/2207.04587/) (2022)
- [Enhancing Neural Network Interpretability with Feature-Aligned Sparse Autoencoders](https://mlsanity.com/paper/2411.01220/) (2024)
- [Injecting Text in Self-Supervised Speech Pretraining](https://mlsanity.com/paper/2108.12226/) (2021)
- [Neural Data-to-Text Generation with LM-based Text Augmentation](https://mlsanity.com/paper/2102.03556/) (2021)
- [Beyond Sparse Rewards: Enhancing Reinforcement Learning with Language Model Critique in Text Generation](https://mlsanity.com/paper/2401.07382/) (2024)
- [Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences](https://mlsanity.com/paper/2506.02095/) (2025)
- [Modeling Dual Read/Write Paths for Simultaneous Machine Translation](https://mlsanity.com/paper/2203.09163/) (2022)
- [Deep Learning for Visual Speech Analysis: A Survey](https://mlsanity.com/paper/2205.10839/) (2022)
- [Sequence-Level Training for Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/2106.08122/) (2021)
- [Dual Attentive Sequential Learning for Cross-Domain Click-Through Rate Prediction](https://mlsanity.com/paper/2106.02768/) (2021)
- [Improving Neural Machine Translation by Bidirectional Training](https://mlsanity.com/paper/2109.07780/) (2021)
- [Meta Back-translation](https://mlsanity.com/paper/2102.07847/) (2021)
- [A Survey on Low-Resource Neural Machine Translation](https://mlsanity.com/paper/2107.04239/) (2021)
- [Modelling Latent Translations for Cross-Lingual Transfer](https://mlsanity.com/paper/2107.11353/) (2021)
- [No-Reference Image Quality Assessment by Hallucinating Pristine Features](https://mlsanity.com/paper/2108.04165/) (2021)
- [There Are a Thousand Hamlets in a Thousand People's Eyes: Enhancing Knowledge-grounded Dialogue with Personal Memory](https://mlsanity.com/paper/2204.02624/) (2022)

## Abstract (arXiv)

While neural machine translation (NMT) is making good progress in the past two years, tens of millions of bilingual sentence pairs are needed for its training. However, human labeling is very costly. To tackle this training data bottleneck, we develop a dual-learning mechanism, which can enable an NMT system to automatically learn from unlabeled data through a dual-learning game. This mechanism is inspired by the following observation: any machine translation task has a dual task, e.g., English-to-French translation (primal) versus French-to-English translation (dual); the primal and dual tasks can form a closed loop, and generate informative feedback signals to train the translation models, even if without the involvement of a human labeler. In the dual-learning mechanism, we use one agent to represent the model for the primal task and the other agent to represent the model for the dual task, then ask them to teach each other through a reinforcement learning process. Based on the feedback signals generated during this process (e.g., the language-model likelihood of the output of a model, and the reconstruction error of the original sentence after the primal and dual translations), we can iteratively update the two models until convergence (e.g., using the policy gradient methods). We call the corresponding approach to neural machine translation dual-NMT. Experiments show that dual-NMT works very well on EnglishleftrightarrowFrench translation; especially, by learning from monolingual data (with 10% bilingual data for warm start), it achieves a comparable accuracy to NMT trained from the full bilingual data for the French-to-English translation task.