Low-Resource Machine Translation through the Lens of Personalized Federated Learning

AmazUtah_NLP at SemEval-2024 Task 9: A MultiChoice Question Answering System for Commonsense Defying Reasoning


View a PDF of the paper titled Low-Resource Machine Translation through the Lens of Personalized Federated Learning, by Viktor Moskvoretskii and 5 other authors

View PDF

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 at this https URL.

Submission history

From: Viktor Moskvoretskii [view email]
[v1]
Tue, 18 Jun 2024 12:50:00 UTC (17,836 KB)
[v2]
Fri, 20 Dec 2024 13:43:47 UTC (17,838 KB)



Source link
lol

By stp2y

Leave a Reply

Your email address will not be published. Required fields are marked *

No widgets found. Go to Widget page and add the widget in Offcanvas Sidebar Widget Area.