Arantza Díaz de Ilarraza
Also known as Arantza Díaz de Ilarraza Sánchez, Arantza Diaz de Ilarraza
Arantza Díaz de Ilarraza is a computer scientist whose career connected intelligent tutoring, Basque spelling tools and machine translation. She began lecturing at the Faculty of Informatics in San Sebastián in 1981 and completed a doctorate on natural-language dialogue for an intelligent teaching system in 1990. In 1994, Xuxen, a Basque spelling checker, reached the public through work by the IXA group, UZEI and Hizkia; she was one of the group's early researchers. She supervised a 2007 thesis on Matxin and joined UPV/EHU's doctoral-school leadership team in 2012. As of October 2026, she is retired after serving as a full professor of informatics and a language-processing researcher at EHU.
Timeline
-
1981
Lecturer in San Sebastián
She begins lecturing at the Faculty of Informatics in San Sebastián in 1981.
-
1990
A doctorate in dialogue systems
At the University of the Basque Country, she completes a doctorate in 1990 on natural-language dialogue for an intelligent teaching system.
-
1994
Xuxen reaches Basque users
In 1994, the IXA group releases Xuxen, a Basque spelling checker it develops with UZEI and Hizkia; she is one of the group's early researchers.
-
2007
Supervising the Matxin thesis
In 2007, she supervises Aingeru Mayor's thesis on Matxin, a rule-based machine-translation system built from broad-coverage linguistic resources; it becomes the first translator developed for Basque.
-
2012
Joining doctoral-school leadership
The UPV/EHU doctoral school adds her to its first leadership team in 2012.
-
As of October 2026
Retired from EHU
She is retired after serving as a full professor of informatics and a researcher in language processing at EHU.
Career
- 2012–2023University of the Basque CountryLeadership Team Member
- From 1981Faculty of InformaticsLecturer
- IXA GroupResearcher
Education
- 1990University of the Basque CountryDoctorate
Most-cited works
- On the creation of a clinical gold standard corpus in Spanish: Mining adverse drug reactions
- Interpretable deep learning to map diagnostic texts to ICD-10 codes
- A Cascaded Syntactic Analyser for Basque
- Matxin, an open-source rule-based machine translation system for Basque
- Multi-label clinical document classification: Impact of label-density
Sources and credits
Photo: We have no published photo of Arantza Díaz de Ilarraza yet. Send us a free-licensed photo.

