Greetings, I'm Oscar!
My academic journey commenced with the attainment of a Bachelor's degree in Computer Science in 2019, which I swiftly followed with a Master's degree in Natural Language Analysis and Processing in 2020. These milestones were achieved at the University of the Basque Country (UPV/EHU). Currently, I am immersed in the pursuit of a Ph.D. in Natural Language Processing at UPV/EHU. Since 2018, I have been an active member of the IXA research group, working hard on NLP research.
My research revolves around two key areas: low-resource information extraction and data contamination. I'm passionate about finding creative solutions to extract meaningful insights from limited data resources, as seen in my work on topics like zero and few-shot information extraction. Additionally, I tackle the challenges of data contamination, aiming to improve data quality and reliability in Natural Language Processing applications.
Showing last 10 publications. For more visit my Google Scholar or Semantic Scholar page.
University of the Basque Country (UPV/EHU)
Hitz Center for
Language Technologies - Ixa group
University of the Basque Country (UPV/EHU)
Grade: 9.26 / 10
Ixa research group
IKASIKER collaboration grant
University of the Basque Country (UPV/EHU)
Grade: 8.06 / 10
Guideline following Large Language Model for Information Extraction
A Framework for Textual Entailment based Zero Shot text classification
The LM Contamination Index is a manually created database of contamination evidences for LMs.
A extension of Transformers library to include T5ForSequenceClassification class.