Parameter-Efficient Finetuning for Robust Continual Multilingual Learning

TL;DR

This paper introduces LAFT-URIEL, a parameter-efficient finetuning method for continual multilingual learning, which improves language performance across updates and reduces performance loss on other languages by leveraging linguistic knowledge.

Contribution

The paper proposes LAFT-URIEL, a novel finetuning strategy that enhances multilingual model updates by balancing knowledge sharing and overfitting using linguistic insights.

Findings

Increases the number of languages with improved performance by 25% after updates.

Reduces average performance loss on remaining languages by 78%.

Addresses the challenge of catastrophic forgetting in continual multilingual learning.

Abstract

We introduce and study the problem of Continual Multilingual Learning (CML) where a previously trained multilingual model is periodically updated using new data arriving in stages. If the new data is present only in a subset of languages, we find that the resulting model shows improved performance only on the languages included in the latest update (and a few closely related languages) while its performance on all the remaining languages degrade significantly. We address this challenge by proposing LAFT-URIEL, a parameter-efficient finetuning strategy which aims to increase the number of languages on which the model improves after an update, while reducing the magnitude of loss in performance for the remaining languages. LAFT-URIEL uses linguistic knowledge to balance overfitting and knowledge sharing across languages, allowing for an additional 25% of task languages to see an improvement in performance after an update, while also reducing the average magnitude of losses on the remaining languages by 78% relative.