The GEBERT model pre-trained with GAT graph encoder.
The model was published at CLEF 2023 conference. The source code is available at github.
Pretraining data: biomedical concept graph and concept names from the UMLS (2020AB release).
Base model: microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext.
@inproceedings{sakhovskiy2023gebert,
author="Sakhovskiy, Andrey
and Semenova, Natalia
and Kadurin, Artur
and Tutubalina, Elena",
title="Graph-Enriched Biomedical Entity Representation Transformer",
booktitle="Experimental IR Meets Multilinguality, Multimodality, and Interaction",
year="2023",
publisher="Springer Nature Switzerland",
address="Cham",
pages="109--120",
isbn="978-3-031-42448-9"
}
- Downloads last month
- 8
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.