# Dual Reconstruction: a Unifying Objective for Semi-Supervised Neural Machine Translation

arXiv: https://arxiv.org/abs/2010.03412 · HTML: https://mlsanity.com/paper/2010.03412/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2020.

## Built on by (most cited first, 7 of 7)

- [Neural Machine Translation for Low-Resource Languages: A Survey](https://mlsanity.com/paper/2106.15115/) (2021)
- [Rule-based Morphological Inflection Improves Neural Terminology Translation](https://mlsanity.com/paper/2109.04620/) (2021)
- [Improving Logical-Level Natural Language Generation with Topic-Conditioned Data Augmentation and Logical Form Generation](https://mlsanity.com/paper/2112.06240/) (2021)
- [Dual-branch Prompting for Multimodal Machine Translation](https://mlsanity.com/paper/2507.17588/) (2025)
- [Shared Latent Space by Both Languages in Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/2305.03511/) (2023)
- [Chem-FINESE: Validating Fine-Grained Few-shot Entity Extraction through Text Reconstruction](https://mlsanity.com/paper/2401.10189/) (2024)
- [End-to-End Training for Back-Translation with Categorical Reparameterization Trick](https://mlsanity.com/paper/2202.08465/) (2022)

## Abstract (arXiv)

While Iterative Back-Translation and Dual Learning effectively incorporate monolingual training data in neural machine translation, they use different objectives and heuristic gradient approximation strategies, and have not been extensively compared. We introduce a novel dual reconstruction objective that provides a unified view of Iterative Back-Translation and Dual Learning. It motivates a theoretical analysis and controlled empirical study on German-English and Turkish-English tasks, which both suggest that Iterative Back-Translation is more effective than Dual Learning despite its relative simplicity.