Modèle de langue obtenu par l'entraînement de l'architecture ELMo sur le sous-corpus français du corpus multilingue à large couverture OSCAR (Ortiz Suárez et al., 2019).
Logo par Alix Chagué.
Si vous utilisez ce travail, merci de citer :
@inproceedings{Ortiz Su{\'a}rez_Establishing-a-New-State-of-the-Art_2020,
address = {Marseille, France},
author = {Ortiz Su{\'a}rez, Pedro Javier and Dupont, Yoann and Muller, Benjamin and Romary, Laurent and Sagot, Beno{\^i}t},
title = {{Establishing a New State-of-the-Art for French Named Entity Recognition}},
year = {2020},
booktitle = {{LREC 2020 - 12th Language Resources and Evaluation Conference}},
url = {https://inria.hal.science/hal-02617950},
note = {Due to COVID19 pandemic, the 12th edition is cancelled. The LREC 2020 Proceedings are available at http://www.lrec-conf.org/proceedings/lrec2020/index.html},
hal_pdf = {https://inria.hal.science/hal-02617950v2/file/lrec19ner.pdf},
}