# Transfer learning and subword sampling for asymmetric-resource one-to-many neural translation

arXiv: https://arxiv.org/abs/2004.04002 · HTML: https://mlsanity.com/paper/2004.04002/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Apr 2020.

## Built on by (most cited first, 2 of 2)

- [Dynamic Acoustic Unit Augmentation With BPE-Dropout for Low-Resource End-to-End Speech Recognition](https://mlsanity.com/paper/2103.07186/) (2021)
- [SemiAdapt and SemiLoRA: Efficient Domain Adaptation for Transformer-based Low-Resource Language Translation with a Case Study on Irish](https://mlsanity.com/paper/2510.18725/) (2025)

## Abstract (arXiv)

There are several approaches for improving neural machine translation for low-resource languages: Monolingual data can be exploited via pretraining or data augmentation; Parallel corpora on related language pairs can be used via parameter sharing or transfer learning in multilingual models; Subword segmentation and regularization techniques can be applied to ensure high coverage of the vocabulary. We review these approaches in the context of an asymmetric-resource one-to-many translation task, in which the pair of target languages are related, with one being a very low-resource and the other a higher-resource language. We test various methods on three artificially restricted translation tasks -- English to Estonian (low-resource) and Finnish (high-resource), English to Slovak and Czech, English to Danish and Swedish -- and one real-world task, Norwegian to North S'ami and Finnish. The experiments show positive effects especially for scheduled multi-task learning, denoising autoencoder, and subword sampling.