# Multilingual Mix: Example Interpolation Improves Multilingual Neural Machine Translation

arXiv: https://arxiv.org/abs/2203.07627 · HTML: https://mlsanity.com/paper/2203.07627/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 44 references that are in the map.
- First posted on arXiv 15 Mar 2022.

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [Beyond English-Centric Multilingual Machine Translation](https://mlsanity.com/paper/2010.11125/) (2020)
- [The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation](https://mlsanity.com/paper/2106.03193/) (2021)
- [Unsupervised Cross-lingual Representation Learning for Speech Recognition](https://mlsanity.com/paper/2006.13979/) (2020)
- [Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation](https://mlsanity.com/paper/1611.04558/) (2016)
- [Synthetic and Natural Noise Both Break Neural Machine Translation](https://mlsanity.com/paper/1711.02173/) (2017)
- [Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation](https://mlsanity.com/paper/2004.11867/) (2020)
- [Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges](https://mlsanity.com/paper/1907.05019/) (2019)
- [Emerging Cross-lingual Structure in Pretrained Language Models](https://mlsanity.com/paper/1911.01464/) (2019)
- [Augmenting Data with Mixup for Sentence Classification: An Empirical Study](https://mlsanity.com/paper/1905.08941/) (2019)
- [Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism](https://mlsanity.com/paper/1601.01073/) (2016)
- [Robust Neural Machine Translation with Doubly Adversarial Inputs](https://mlsanity.com/paper/1906.02443/) (2019)
- [The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation](https://mlsanity.com/paper/1804.09849/) (2018)
- [Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling](https://mlsanity.com/paper/1902.08295/) (2019)
- [Jointly Learning to Align and Translate with Transformer Models](https://mlsanity.com/paper/1909.02074/) (2019)
- [Sequence-Level Mixed Sample Data Augmentation](https://mlsanity.com/paper/2011.09039/) (2020)
- [Investigating Multilingual NMT Representations at Scale](https://mlsanity.com/paper/1909.02197/) (2019)
- [AdvAug: Robust Adversarial Augmentation for Neural Machine Translation](https://mlsanity.com/paper/2006.11834/) (2020)
- [The Missing Ingredient in Zero-Shot Neural Machine Translation](https://mlsanity.com/paper/1903.07091/) (2019)
- [Zero-Resource Translation with Multi-Lingual Neural Machine Translation](https://mlsanity.com/paper/1606.04164/) (2016)

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

- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability](https://mlsanity.com/paper/2212.10888/) (2022)
- [A Survey on Mixup Augmentations and Beyond](https://mlsanity.com/paper/2409.05202/) (2024)
- [Cross-modality Data Augmentation for End-to-End Sign Language Translation](https://mlsanity.com/paper/2305.11096/) (2023)
- [Mu2SLAM: Multitask, Multilingual Speech and Language Models](https://mlsanity.com/paper/2212.09553/) (2022)
- [Adapting to Non-Centered Languages for Zero-shot Multilingual Translation](https://mlsanity.com/paper/2209.04138/) (2022)
- [Mix-MoE: Improving Multilingual Machine Translation of Large Language Models through Mixed MoEs](https://mlsanity.com/paper/2605.24681/) (2026)

## Abstract (arXiv)

Multilingual neural machine translation models are trained to maximize the likelihood of a mix of examples drawn from multiple language pairs. The dominant inductive bias applied to these models is a shared vocabulary and a shared set of parameters across languages; the inputs and labels corresponding to examples drawn from different language pairs might still reside in distinct sub-spaces. In this paper, we introduce multilingual crossover encoder-decoder (mXEncDec) to fuse language pairs at an instance level. Our approach interpolates instances from different language pairs into joint `crossover examples' in order to encourage sharing input and output spaces across languages. To ensure better fusion of examples in multilingual settings, we propose several techniques to improve example interpolation across dissimilar languages under heavy data imbalance. Experiments on a large-scale WMT multilingual dataset demonstrate that our approach significantly improves quality on English-to-Many, Many-to-English and zero-shot translation tasks (from +0.5 BLEU up to +5.5 BLEU points). Results on code-switching sets demonstrate the capability of our approach to improve model generalization to out-of-distribution multilingual examples. We also conduct qualitative and quantitative representation comparisons to analyze the advantages of our approach at the representation level.