Efficient Architectures for Low-resource Machine Translation

ACL ARR 2025 February Submission4803 Authors

Abstract: Low-resource Neural Machine Translation is highly sensitive to hyperparameters and needs careful tuning to achieve the best results with small amounts of training data. We focus on exploring the impact of changes in the Transformer architecture on downstream translation quality, and propose a metric to score the computational efficiency of such changes. By experimenting on English-Akkadian, German-Lower Sorbian, English-Italian, and English-Manipuri, we confirm previous finding in low-resource machine translation optimization, and show that smaller and more parameter-efficient models can achieve the same translation quality of larger and unwieldy ones at a fraction of the computational cost.

Paper Type: Long

Research Area: Efficient/Low-Resource Methods for NLP

Research Area Keywords: parameter-efficient-training, NLP in resource-constrained settings, efficient MT training, scaling

Contribution Types: Approaches to low-resource settings, Approaches low compute settings-efficiency

Languages Studied: English, Italian, Akkadian, German, Lower Sorbian, Manipuri

Submission Number: 4803