Parameter-Efficient Finetuning for Robust Continual Multilingual Learning
This addresses the challenge of maintaining robust performance across all languages in continual multilingual learning, which is incremental as it builds on existing finetuning methods.
The paper tackles the problem of performance degradation in multilingual models when updated with data from only a subset of languages, proposing a parameter-efficient finetuning strategy that increases the number of languages showing improvement by 25% and reduces average performance losses on other languages by 78%.
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.