Duration: 1:47:05

1,327 views

31

Watch our two-hour grand seminar on Large Language Models and Low Resource Languages. The event included a keynote by Dr. Monojit Choudhury titled “Predicting, Explaining and Optimizing Performance of LLMs across Languages,” where he discussed whether massively multilingual language models (MMLM) can be leveraged to predict the accuracy of cross-lingual zero-shot and few-shot transfer for a task on target languages with little or no test data. He also gave an overview of Project LITMUS – Linguistically Informed Training and Testing of Multilingual Systems, which involved building several ML models for performance prediction and discuss the what was learnt about the factors that influence cross-lingual transfer.

The talk was followed by a panel discussion with experts from academia and research; including Dr. Monojit Chowdhury, Dr. Edward Ombui, Dr. Sunayana Sitaram, Dr. David Adelani, and moderated by Maxamed Axmed.


Keynote Abstract:

Predicting, Explaining and Optimizing Performance of LLMs across Languages

Given a massively multilingual language models (MMLM), can we predict the accuracy of cross-lingual zero-shot and few-shot transfer for a task on target languages with little or no test data? This seemingly impossible task, if solved, can have several potential benefits. First, we could estimate the performance of a model even in languages where a test set is not available, and/or building one is difficult. Second, one can predict training data configurations that would give certain desired performance across a set of languages, and accordingly strategize data collection plans; this in turn can lead to linguistically fair MMLM-based models. Third, as a byproduct, we would know which factors influence cross-lingual transfer. In this talk, I will give an overview of Project LITMUS – Linguistically Informed Training and Testing of Multilingual Systems, where we build several ML models for performance prediction; besides their applications, I will discuss what we learn about the factors that influence cross-lingual transfer.

Learn more about MARI: https://www.microsoft.com/en-us/research/group/microsoft-africa-research-institute-mari/