This repository contains resources and tools for Named Entity Recognition in Modern Greek aligned with the Universal NER (UNER) framework.
This is a follow-up to previous work on Greek NER (Demiros et al., 2000; Giouli et al., 2006). Moreover, Greek remains underrepresented in multilingual NER benchmarks. This project aims to fill that gap by providing open datasets, models, and tools to support research and applications in Greek NER.
Annotated Greek corpus following UNER guidelines
Baseline NER classifier using transformer-based models (to be available soon
Preprocessing and annotation conversion scripts (to be available soon)
Annotation guidelines tailored for Greek (to be available soon)
Evaluation tools and metrics (to be available soon)
Iason Demiros, Sotiris Boutsis, Voula Giouli, Maria Liakata, Harris Papageorgiou, and Stelios Piperidis. 2000. Named Entity Recognition in Greek Texts. In Proceedings of the Second International Conference on Language Resources and Evaluation (LREC’00), Athens, Greece. European Language Resources Association (ELRA).
Voula Giouli, Alexis Konstandinidis, Elina Desypri, and Harris Papageorgiou. 2006. Multi-domain Multi-lingual Named Entity Recognition: Revisiting & Grounding the resources issue. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06), Genoa, Italy. European Language Resources Association (ELRA).