I am Ramon y Cajal Research Fellow (tenure-track) at IXA Group, part of the HiTZ Centre of the University of the Basque Country UPV/EHU. PhD in Computer Science at City, University of London (2007), I have since been working on Natural Language Processing at several British and Spanish institutions, including a two year stint at the industry as research project director. I have been involved in more than 20 research projects funded by the European Commission, UK research councils, Spanish Ministry of Science and Basque Goverment. I was technical coordinator of the European project SUMAT and got awarded a Torres Quevedo Research Fellowship.
Recently I have been PI of an H2020 OPENMINTED Tender Call Phase II project and Working Group leader within the enetCollect COST action. Currently I am Co-IP (with German Rigau) of “DeepReading: DeepReading: Mining, Understanding, and Reasoning with Multilingual Content”, a project funded by the Spanish Ministry of Science.
Currently my research is focused on Computational Semantics and Information Extraction (Named Entity Recognition, Opinion Mining, Fake News and Stance detection, etc.), especially in multilingual and cross-lingual approaches. I am the creator and main developer of IXA pipes, a set of ready to use multilingual tools for linguistic processing. I am also PMC and committer in the OpenNLP project of the Apache Software Foundation. Due to this association I have been mentor in the Google Summer of Code (GSOC).
New paper on Multilingual Stance Detection published at Expert Systems with Applications, Elsevier.
Invited to the IJCAI 2020 Journal track: We have been invited to publish our paper Language Independent Sequence Labelling for Opinion Target Extraction, Artificial Intelligence Journal, 2019. preprint version available
New project funded: I am co-PI (with Simón Peña-Fernandez) of the project: “Tools for the analysis of parliamentary discourses: polarization, subjectivity and affectivity in the post-truth era”. Funded by the UPV/EHU to promote collaboration between GureIker and IXA research groups.
Two papers accepted at LREC 2020
“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).