Ainhoa Vivel Couso

In 2021, I was awarded a summer research scholarship at CiTIUS, where I began my research activity in the field of Natural Language Technologies. In 2022, I participated in the Nós Project, contributing to the creation of textual linguistic resources for Galician with the aim of supporting its integration into Natural Language Processing (NLP) tools. In 2023, I was the winner of the 4th edition of the Altia Premia Awards for my Bachelor's Thesis, which focused on the automatic generation of natural language descriptions to justify estimated chronological age using a deep learning-based method. Between 2023 and 2024, I worked at the Research Centre on Intelligent Technologies (CiTIUS) as a research assistant, participating in the REPROHUM and DeepR3 projects.

In 2024, I was awarded a predoctoral research grant from the Xunta de Galicia (ED481A-2024-059). Since then, I have been pursuing my PhD at CiTIUS, focusing on text simplification and explainability in language models, as well as on the development of efficient and energy-efficient methods for extending, reusing, and adapting language models to new domains, genres, and languages. As part of my research, I conduct reproducibility and repeatability studies of published experiments, as well as train and adapt language models using knowledge transfer techniques, with the aim of investigating efficient strategies for reusing and adapting pretrained models to new contexts.