When does Parameter-Efficient Transfer Learning Work for Machine Translation?

Ahmet Üstün, Asa Cooper Stickland


Abstract
Parameter-efficient fine-tuning methods (PEFTs) offer the promise of adapting large pre-trained models while only tuning a small number of parameters. They have been shown to be competitive with full model fine-tuning for many downstream tasks. However, prior work indicates that PEFTs may not work as well for machine translation (MT), and there is no comprehensive study showing when PEFTs work for MT. We conduct a comprehensive empirical study of PEFTs for MT, considering (1) various parameter budgets, (2) a diverse set of language-pairs, and (3) different pre-trained models. We find that ‘adapters’, in which small feed-forward networks are added after every layer, are indeed on par with full model fine-tuning when the parameter budget corresponds to 10% of total model parameters. Nevertheless, as the number of tuned parameters decreases, the performance of PEFTs decreases. The magnitude of this decrease depends on the language pair, with PEFTs particularly struggling for distantly related language-pairs. We find that using PEFTs with a larger pre-trained model outperforms full fine-tuning with a smaller model, and for smaller training data sizes, PEFTs outperform full fine-tuning for the same pre-trained model.
Anthology ID:
2022.emnlp-main.540
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7919–7933
Language:
URL:
https://aclanthology.org/2022.emnlp-main.540
DOI:
10.18653/v1/2022.emnlp-main.540
Bibkey:
Cite (ACL):
Ahmet Üstün and Asa Cooper Stickland. 2022. When does Parameter-Efficient Transfer Learning Work for Machine Translation?. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 7919–7933, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
When does Parameter-Efficient Transfer Learning Work for Machine Translation? (Üstün & Cooper Stickland, EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.540.pdf