# Target-Side Augmentation for Document-Level Machine Translation

arXiv: https://arxiv.org/abs/2305.04505 · HTML: https://mlsanity.com/paper/2305.04505/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 69 references that are in the map.
- First posted on arXiv 8 May 2023.

## Builds on (most cited first, 30 of 43)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [Reconciling modern machine learning practice and the bias-variance trade-off](https://mlsanity.com/paper/1812.11118/) (2018)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [Sequence-Level Knowledge Distillation](https://mlsanity.com/paper/1606.07947/) (2016)
- [Improving Neural Machine Translation Models with Monolingual Data](https://mlsanity.com/paper/1511.06709/) (2015)
- [Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates](https://mlsanity.com/paper/1804.10959/) (2018)
- [Do Deep Nets Really Need to be Deep?](https://mlsanity.com/paper/1312.6184/) (2013)
- [PAWS: Paraphrase Adversaries from Word Scrambling](https://mlsanity.com/paper/1904.01130/) (2019)
- [Rethinking Pre-training and Self-training](https://mlsanity.com/paper/2006.06882/) (2020)
- [Six Challenges for Neural Machine Translation](https://mlsanity.com/paper/1706.03872/) (2017)
- [Revisiting Self-Training for Neural Sequence Generation](https://mlsanity.com/paper/1909.13788/) (2019)
- [Data Augmentation for Low-Resource Neural Machine Translation](https://mlsanity.com/paper/1705.00440/) (2017)
- [Gender Bias in Machine Translation](https://mlsanity.com/paper/2104.06001/) (2021)
- [Conditional BERT Contextual Augmentation](https://mlsanity.com/paper/1812.06705/) (2018)
- [Document-Level Neural Machine Translation with Hierarchical Attention Networks](https://mlsanity.com/paper/1809.01576/) (2018)
- [Data Augmentation Approaches in Natural Language Processing: A Survey](https://mlsanity.com/paper/2110.01852/) (2021)
- [Reward Augmented Maximum Likelihood for Neural Structured Prediction](https://mlsanity.com/paper/1609.00150/) (2016)
- [Autoregressive Knowledge Distillation through Imitation Learning](https://mlsanity.com/paper/2009.07253/) (2020)
- [SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation](https://mlsanity.com/paper/1808.07512/) (2018)
- [Selective Attention for Context-aware Neural Machine Translation](https://mlsanity.com/paper/1903.08788/) (2019)
- [The paradox of the compositionality of natural language: a neural machine translation case study](https://mlsanity.com/paper/2108.05885/) (2021)
- [Microsoft Translator at WMT 2019: Towards Large-Scale Document-Level Neural Machine Translation](https://mlsanity.com/paper/1907.06170/) (2019)
- [G-Transformer for Document-level Machine Translation](https://mlsanity.com/paper/2105.14761/) (2021)
- [Variational Neural Machine Translation](https://mlsanity.com/paper/1605.07869/) (2016)

## Built on by (most cited first, 5 of 5)

- [To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation](https://mlsanity.com/paper/2401.01419/) (2024)
- [DeMPT: Decoding-enhanced Multi-phase Prompt Tuning for Making LLMs Be Better Context-aware Translators](https://mlsanity.com/paper/2402.15200/) (2024)
- [Context-Aware Machine Translation with Source Coreference Explanation](https://mlsanity.com/paper/2404.19505/) (2024)
- [Non-Autoregressive Document-Level Machine Translation](https://mlsanity.com/paper/2305.12878/) (2023)
- [Interpretable Style Takagi-Sugeno-Kang Fuzzy Clustering](https://mlsanity.com/paper/2504.05125/) (2025)

## Abstract (arXiv)

Document-level machine translation faces the challenge of data sparsity due to its long input length and a small amount of training data, increasing the risk of learning spurious patterns. To address this challenge, we propose a target-side augmentation method, introducing a data augmentation (DA) model to generate many potential translations for each source document. Learning on these wider range translations, an MT model can learn a smoothed distribution, thereby reducing the risk of data sparsity. We demonstrate that the DA model, which estimates the posterior distribution, largely improves the MT performance, outperforming the previous best system by 2.30 s-BLEU on News and achieving new state-of-the-art on News and Europarl benchmarks. Our code is available at https://github.com/baoguangsheng/target-side-augmentation.