# Unsupervised Neural Machine Translation for Low-Resource Domains via Meta-Learning

arXiv: https://arxiv.org/abs/2010.09046 · HTML: https://mlsanity.com/paper/2010.09046/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Oct 2020.

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

- [Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey](https://mlsanity.com/paper/2104.06951/) (2021)
- [Meta Learning for Natural Language Processing: A Survey](https://mlsanity.com/paper/2205.01500/) (2022)
- [Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey](https://mlsanity.com/paper/2208.03197/) (2022)
- [Learning to Adapt to Low-Resource Paraphrase Generation](https://mlsanity.com/paper/2412.17111/) (2024)
- [BrailleLLM: Braille Instruction Tuning with Large Language Models for Braille Domain Tasks](https://mlsanity.com/paper/2510.18288/) (2025)
- [High-Resource Methodological Bias in Low-Resource Investigations](https://mlsanity.com/paper/2211.07534/) (2022)
- [Reinforcement Learning for Few-Shot Text Generation Adaptation](https://mlsanity.com/paper/2111.11030/) (2021)
- [Epi-Curriculum: Episodic Curriculum Learning for Low-Resource Domain Adaptation in Neural Machine Translation](https://mlsanity.com/paper/2309.02640/) (2023)
- [Domain Adaptation of Multilingual Semantic Search -- Literature Review](https://mlsanity.com/paper/2402.02932/) (2024)

## Abstract (arXiv)

Unsupervised machine translation, which utilizes unpaired monolingual corpora as training data, has achieved comparable performance against supervised machine translation. However, it still suffers from data-scarce domains. To address this issue, this paper presents a novel meta-learning algorithm for unsupervised neural machine translation (UNMT) that trains the model to adapt to another domain by utilizing only a small amount of training data. We assume that domain-general knowledge is a significant factor in handling data-scarce domains. Hence, we extend the meta-learning algorithm, which utilizes knowledge learned from high-resource domains, to boost the performance of low-resource UNMT. Our model surpasses a transfer learning-based approach by up to 2-4 BLEU scores. Extensive experimental results show that our proposed algorithm is pertinent for fast adaptation and consistently outperforms other baseline models.