# Adapting Multilingual Neural Machine Translation to Unseen Languages

arXiv: https://arxiv.org/abs/1910.13998 · HTML: https://mlsanity.com/paper/1910.13998/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Oct 2019.

## Built on by (most cited first, 12 of 12)

- [Neural Machine Translation for Low-Resource Languages: A Survey](https://mlsanity.com/paper/2106.15115/) (2021)
- [Towards Continual Learning for Multilingual Machine Translation via Vocabulary Substitution](https://mlsanity.com/paper/2103.06799/) (2021)
- [Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data](https://mlsanity.com/paper/2105.15071/) (2021)
- [Continual Learning in Multilingual NMT via Language-Specific Embeddings](https://mlsanity.com/paper/2110.10478/) (2021)
- [First Attempt at Building Parallel Corpora for Machine Translation of Northeast India's Very Low-Resource Languages](https://mlsanity.com/paper/2312.04764/) (2023)
- [Continual Knowledge Distillation for Neural Machine Translation](https://mlsanity.com/paper/2212.09097/) (2022)
- [EdinSaar@WMT21: North-Germanic Low-Resource Multilingual NMT](https://mlsanity.com/paper/2109.14368/) (2021)
- [Efficiently Upgrading Multilingual Machine Translation Models to Support More Languages](https://mlsanity.com/paper/2302.03528/) (2023)
- [Self-Learning for Zero Shot Neural Machine Translation](https://mlsanity.com/paper/2103.05951/) (2021)
- [The VolcTrans System for WMT22 Multilingual Machine Translation Task](https://mlsanity.com/paper/2210.11599/) (2022)
- [The Influence of Iconicity in Transfer Learning for Sign Language Recognition](https://mlsanity.com/paper/2603.03316/) (2026)
- [Precision over Scale: A Polish-Silesian Benchmark and a Translation System Outperforming Open-Source and Commercial Models](https://mlsanity.com/paper/2610.01082/) (2026)

## Abstract (arXiv)

Multilingual Neural Machine Translation (MNMT) for low-resource languages (LRL) can be enhanced by the presence of related high-resource languages (HRL), but the relatedness of HRL usually relies on predefined linguistic assumptions about language similarity. Recently, adapting MNMT to a LRL has shown to greatly improve performance. In this work, we explore the problem of adapting an MNMT model to an unseen LRL using data selection and model adaptation. In order to improve NMT for LRL, we employ perplexity to select HRL data that are most similar to the LRL on the basis of language distance. We extensively explore data selection in popular multilingual NMT settings, namely in (zero-shot) translation, and in adaptation from a multilingual pre-trained model, for both directions (LRL-en). We further show that dynamic adaptation of the model's vocabulary results in a more favourable segmentation for the LRL in comparison with direct adaptation. Experiments show reductions in training time and significant performance gains over LRL baselines, even with zero LRL data (+13.0 BLEU), up to +17.0 BLEU for pre-trained multilingual model dynamic adaptation with related data selection. Our method outperforms current approaches, such as massively multilingual models and data augmentation, on four LRL.