# Exploiting Out-of-Domain Parallel Data through Multilingual Transfer Learning for Low-Resource Neural Machine Translation

arXiv: https://arxiv.org/abs/1907.03060 · HTML: https://mlsanity.com/paper/1907.03060/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jul 2019.

## Built on by (most cited first, 11 of 11)

- [Neural Machine Translation for Low-Resource Languages: A Survey](https://mlsanity.com/paper/2106.15115/) (2021)
- [Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation](https://mlsanity.com/paper/2105.03953/) (2021)
- [Gradual Fine-Tuning for Low-Resource Domain Adaptation](https://mlsanity.com/paper/2103.02205/) (2021)
- [adaptMLLM: Fine-Tuning Multilingual Language Models on Low-Resource Languages with Integrated LLM Playgrounds](https://mlsanity.com/paper/2403.02370/) (2024)
- [Learning to Parallelize in a Shared-Memory Environment with Transformers](https://mlsanity.com/paper/2204.12835/) (2022)
- [CreoleVal: Multilingual Multitask Benchmarks for Creoles](https://mlsanity.com/paper/2310.19567/) (2023)
- [Leveraging Auxiliary Domain Parallel Data in Intermediate Task Fine-tuning for Low-resource Translation](https://mlsanity.com/paper/2306.01382/) (2023)
- [Attentive fine-tuning of Transformers for Translation of low-resourced languages @LoResMT 2021](https://mlsanity.com/paper/2108.08556/) (2021)
- [Human Evaluation of English--Irish Transformer-Based NMT](https://mlsanity.com/paper/2403.02366/) (2024)
- [Exploiting Domain-Specific Parallel Data on Multilingual Language Models for Low-resource Language Translation](https://mlsanity.com/paper/2412.19522/) (2024)
- [The University of Melbourne WMT 2026 CreoleMT Submission: A Domain-Balanced Approach to Low-Resource Pacific Creole Machine Translation](https://mlsanity.com/paper/2609.13615/) (2026)

## Abstract (arXiv)

This paper proposes a novel multilingual multistage fine-tuning approach for low-resource neural machine translation (NMT), taking a challenging Japanese--Russian pair for benchmarking. Although there are many solutions for low-resource scenarios, such as multilingual NMT and back-translation, we have empirically confirmed their limited success when restricted to in-domain data. We therefore propose to exploit out-of-domain data through transfer learning, by using it to first train a multilingual NMT model followed by multistage fine-tuning on in-domain parallel and back-translated pseudo-parallel data. Our approach, which combines domain adaptation, multilingualism, and back-translation, helps improve the translation quality by more than 3.7 BLEU points, over a strong baseline, for this extremely low-resource scenario.