Low-Resource Machine Translation through the Lens of Personalized Federated Learning
Viktor Moskvoretskii, Nazarii Tupitsa, Chris Biemann, Samuel Horváth, Eduard Gorbunov, Irina Nikishina
Abstract
We present a new approach called MeritOpt based on the Personalized Federated Learning algorithm MeritFed that can be applied to Natural Language Tasks with heterogeneous data. We evaluate it on the Low-Resource Machine Translation task, using the datasets of South East Asian and Finno-Ugric languages. In addition to its effectiveness, MeritOpt is also highly interpretable, as it can be applied to track the impact of each language used for training. Our analysis reveals that target dataset size affects weight distribution across auxiliary languages, that unrelated languages do not interfere with the training, and auxiliary optimizer parameters have minimal impact. Our approach is easy to apply with a few lines of code, and we provide scripts for reproducing the experiments (https://github.com/VityaVitalich/MeritOpt).
BibTeX
@inproceedings{moskvoretskii-etal-2024-low,
title = "Low-Resource Machine Translation through the Lens of Personalized Federated Learning",
author = "Moskvoretskii, Viktor and
Tupitsa, Nazarii and
Biemann, Chris and
Horv{\'a}th, Samuel and
Gorbunov, Eduard and
Nikishina, Irina",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.514/",
doi = "10.18653/v1/2024.findings-emnlp.514",
pages = "8806--8825"
}