I am a Permanent Researcher (tenured) at IXA Group, part of the HiTZ Centre of the University of the Basque Country UPV/EHU, where I am head of the Text Analysis unit. I got a PhD in Computer Science at City, University of London (2007), and I have since been working on Natural Language Processing at several British and Spanish institutions. I have been involved as PI or collaborator in more than 40 research projects funded by the European Commission, UK research councils, Spanish Ministry of Science, and Basque Government and published in the major journals (Artificial Intelligence, Computational Linguistics…) and conferences (ACL, EMNLP, EACL, IJCAI, etc.) related to Artificial Intelligence and Natural Language Processing.

My research is focused on multilingual and crosslingual Natural Language Processing, information extraction, semantic processing, and large language models, with a particular interest in high-impact applications in specialized domains. I am currently the Principal Investigator of four projects: CRITICS (2025–2028), a European CHIST-ERA IV Cofund project on multilingual translation of scientific knowledge with LLMs; DeepThought (2025-2028), a coordinated project on reasoning and alignment of large language models for multilingual and low-resource scenarios; DeepMinor (2024–2026), focused on multilingual and multidomain language models and benchmarks for low-resource settings; and DeepKnowledge (2022–2026), which explores deep language models for multilingual understanding and reasoning.

I teach Natural Language Processing at undergraduate, master’s, and doctoral levels, including the international online course Introduction to Language Technology Applications. I have supervised four completed PhD theses and am currently co-supervising 9 fully funded doctoral students and 6 master’s students.

Latest News

Final Word

“If it were not for the brute fact that the world contains more than five billion primates that are demonstrably able to produce and comprehend natural languages, mathematical linguists would long ago have been able to present convincing formal demonstrations that such production and comprehension was impossible” (Gerald Gazdar).