# Understanding and Mitigating the Uncertainty in Zero-Shot Translation

arXiv: https://arxiv.org/abs/2205.10068 · HTML: https://mlsanity.com/paper/2205.10068/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 48 references that are in the map.
- First posted on arXiv 20 May 2022.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Beyond English-Centric Multilingual Machine Translation](https://mlsanity.com/paper/2010.11125/) (2020)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation](https://mlsanity.com/paper/1611.04558/) (2016)
- [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://mlsanity.com/paper/2008.00401/) (2020)
- [Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation](https://mlsanity.com/paper/2004.11867/) (2020)
- [Using the Output Embedding to Improve Language Models](https://mlsanity.com/paper/1608.05859/) (2016)
- [Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges](https://mlsanity.com/paper/1907.05019/) (2019)
- [Massively Multilingual Neural Machine Translation](https://mlsanity.com/paper/1903.00089/) (2019)
- [WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia](https://mlsanity.com/paper/1907.05791/) (2019)
- [Analyzing Uncertainty in Neural Machine Translation](https://mlsanity.com/paper/1803.00047/) (2018)
- [When and Why are Pre-trained Word Embeddings Useful for Neural Machine Translation?](https://mlsanity.com/paper/1804.06323/) (2018)
- [Contrastive Learning for Many-to-many Multilingual Neural Machine Translation](https://mlsanity.com/paper/2105.09501/) (2021)
- [Edinburgh Neural Machine Translation Systems for WMT 16](https://mlsanity.com/paper/1606.02891/) (2016)
- [Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations](https://mlsanity.com/paper/1906.01181/) (2019)
- [Cross-lingual Retrieval for Iterative Self-Supervised Training](https://mlsanity.com/paper/2006.09526/) (2020)
- [Learning Language Specific Sub-network for Multilingual Machine Translation](https://mlsanity.com/paper/2105.09259/) (2021)
- [Improving Zero-Shot Translation by Disentangling Positional Information](https://mlsanity.com/paper/2012.15127/) (2020)
- [Improving Multilingual Translation by Representation and Gradient Regularization](https://mlsanity.com/paper/2109.04778/) (2021)
- [Language Tags Matter for Zero-Shot Neural Machine Translation](https://mlsanity.com/paper/2106.07930/) (2021)
- [Neural Machine Translation with Reconstruction](https://mlsanity.com/paper/1611.01874/) (2016)
- [Rethinking the Value of Transformer Components](https://mlsanity.com/paper/2011.03803/) (2020)
- [Consistency by Agreement in Zero-shot Neural Machine Translation](https://mlsanity.com/paper/1904.02338/) (2019)
- [Data Rejuvenation: Exploiting Inactive Training Examples for Neural Machine Translation](https://mlsanity.com/paper/2010.02552/) (2020)
- [Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translation](https://mlsanity.com/paper/2106.00941/) (2021)
- [Language Models are Good Translators](https://mlsanity.com/paper/2106.13627/) (2021)
- [Rethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variables](https://mlsanity.com/paper/2109.04705/) (2021)
- [On the Language Coverage Bias for Neural Machine Translation](https://mlsanity.com/paper/2106.03297/) (2021)

## Built on by (most cited first, 9 of 9)

- [Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine](https://mlsanity.com/paper/2301.08745/) (2023)
- [Tencent's Multilingual Machine Translation System for WMT22 Large-Scale African Languages](https://mlsanity.com/paper/2210.09644/) (2022)
- [Unlikelihood Tuning on Negative Samples Amazingly Improves Zero-Shot Translation](https://mlsanity.com/paper/2309.16599/) (2023)
- [Improving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features](https://mlsanity.com/paper/2408.01394/) (2024)
- [Uncertainty Quantification for Evaluating Machine Translation Bias](https://mlsanity.com/paper/2507.18338/) (2025)
- [LCS: A Language Converter Strategy for Zero-Shot Neural Machine Translation](https://mlsanity.com/paper/2406.02876/) (2024)
- [PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training](https://mlsanity.com/paper/2507.14202/) (2025)
- [NLIP_Lab-IITH Low-Resource MT System for WMT24 Indic MT Shared Task](https://mlsanity.com/paper/2410.03215/) (2024)
- [On the Shortcut Learning in Multilingual Neural Machine Translation](https://mlsanity.com/paper/2411.10581/) (2024)

## Abstract (arXiv)

Zero-shot translation is a promising direction for building a comprehensive multilingual neural machine translation~(MNMT) system. However, its quality is still not satisfactory due to off-target issues. In this paper, we aim to understand and alleviate the off-target issues from the perspective of uncertainty in zero-shot translation. By carefully examining the translation output and model confidence, we identify two uncertainties that are responsible for the off-target issues, namely, extrinsic data uncertainty and intrinsic model uncertainty. Based on the observations, we propose two lightweight and complementary approaches to denoise the training data for model training and explicitly penalize the off-target translations by unlikelihood training during model training. Extensive experiments on both balanced and imbalanced datasets show that our approaches significantly improve the performance of zero-shot translation over strong MNMT baselines.