This tutorial shows how to use the OTT-JAX toolbox to implement ideas from Entropic Estimation of Optimal Transport Maps.

This work presents an approach for fine-tuning pre-trained language models to perform dialog act classification or sentiment/emotion analysis.

The project aimed to build a performing model associating genre labels with each music title in a database using audio signal data and listener-related information, operating within a multi-label classification framework.

Recent research work has highlighted the growing effectiveness of generative language models in the production of accurate and coherent textual content. By exploiting this technology, this project aimed to develop a system capable of automatically composing questions and answers on predefined topics.