Offensive Language Detection Model for Modern Greek

This model is fine-tuned to detect offensive language in Greek texts (Twitter & Fiction).

Model Details

• Pretrained on nlpaueb/bert-base-greek-uncased-v1
• Fine-tuned on a custom offensive language detection dataset, namely the AIKIA corpus.

Labels

• 0: NOT offensive
• 1: OFFENSIVE language

Citation

@inproceedings{markantonatou-etal-2024-corpus, title = {The Corpus {AIKIA}: Using Ranking Annotation for Offensive Language Detection in {M}odern {G}reek}, author = {Markantonatou, Stella and Stamou, Vivian and Christodoulou, Christina and Apostolopoulou, Georgia and Balas, Antonis and Ioannakis, George}, editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen}, booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)}, month = {may}, year = {2024}, address = {Torino, Italia}, publisher = {ELRA and ICCL}, url = {https://aclanthology.org/2024.lrec-main.1378}, pages = {15861--15871}