GBERT-BioM-Translation-large

This model is a medically continuously pre-trained version of deepset/gbert-large.

Training data

The model was trained on German PubMed abstracts, translated English PubMed abstracts, and translated MIMIC-III reports.

Dataset	Tokens	Documents
German PubMed	5M	16K
PubMed	1,700M	21M
MIMIC-III	695M	24M
Total	2,400M	45M

Evaluation

Model	CLEF eHealth 2019			RadQA		GraSCCo			BRONCO150			GGPONC 2.0
	F1	P	R	F1	EM	F1	P	R	F1	P	R	F1	P	R
GBERT-base	.816	.818	.815	.794	.707	.642	.617	.676	.833	.818	.849	.770	.761	.780
GBERT-large	.832	.802	.865	.809	.718	.647	.617	.680	.835	.820	.852	.772	.758	.786
GBERT-BioM-Translation-base	.825	.851	.801	.808	.716	.661	.642	.681	.842	.824	.861	.780	.766	.794
GBERT-BioM-Translation-large	.833	.860	.807	.811	.714	.692	.677	.707	.844	.825	.864	.786	.779	.793

Publication

@misc{idrissiyaghir2024comprehensive,
      title={Comprehensive Study on German Language Models for Clinical and Biomedical Text Understanding}, 
      author={Ahmad Idrissi-Yaghir and Amin Dada and Henning Schäfer and Kamyar Arzideh and Giulia Baldini and Jan Trienes and Max Hasin and Jeanette Bewersdorff and Cynthia S. Schmidt and Marie Bauer and Kaleb E. Smith and Jiang Bian and Yonghui Wu and Jörg Schlötterer and Torsten Zesch and Peter A. Horn and Christin Seifert and Felix Nensa and Jens Kleesiek and Christoph M. Friedrich},
      year={2024},
      eprint={2404.05694},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}