Multi Task Learning For Zero Shot Performance Prediction of Multilingual Models
This work addresses performance variability in multilingual AI models for researchers and practitioners, but it is incremental as it builds on existing techniques.
The paper tackles the problem of predicting zero-shot performance of multilingual models across languages by modeling it as a multi-task learning approach, resulting in more accurate predictors and robust feature selection for tasks with limited test data.
Massively Multilingual Transformer based Language Models have been observed to be surprisingly effective on zero-shot transfer across languages, though the performance varies from language to language depending on the pivot language(s) used for fine-tuning. In this work, we build upon some of the existing techniques for predicting the zero-shot performance on a task, by modeling it as a multi-task learning problem. We jointly train predictive models for different tasks which helps us build more accurate predictors for tasks where we have test data in very few languages to measure the actual performance of the model. Our approach also lends us the ability to perform a much more robust feature selection and identify a common set of features that influence zero-shot performance across a variety of tasks.