Unlocking Parameter-Efficient Fine-Tuning for Low-Resource Language Translation
Tong Su, Xin Peng, Sarubi Thillainathan, David Guzmán, Surangika Ranathunga, En-Shiun Lee
Abstract
Parameter-efficient fine-tuning (PEFT) methods are increasingly vital in adapting large-scale pre-trained language models for diverse tasks, offering a balance between adaptability and computational efficiency. They are important in Low-Resource Language (LRL) Neural Machine Translation (NMT) to enhance translation accuracy with minimal resources. However, their practical effectiveness varies significantly across different languages. We conducted comprehensive empirical experiments with varying LRL domains and sizes to evaluate the performance of 8 PEFT methods with in total of 15 architectures using the SacreBLEU score. We showed that 6 PEFT architectures outperform the baseline for both in-domain and out-domain tests and the Houlsby+Inversion adapter has the best performance overall, proving the effectiveness of PEFT methods.
BibTeX
@inproceedings{su-etal-2024-unlocking,
title = "Unlocking Parameter-Efficient Fine-Tuning for Low-Resource Language Translation",
author = "Su, Tong and
Peng, Xin and
Thillainathan, Sarubi and
Guzm{\'a}n, David and
Ranathunga, Surangika and
Lee, En-Shiun",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.263/",
doi = "10.18653/v1/2024.findings-naacl.263",
pages = "4217--4225"
}