pruas/BENT-PubMedBERT-NER-Organism

Named Entity Recognition (NER) model to recognize organism entities.

Please cite our work:

@article{NILNKER2022,
  title = {NILINKER: Attention-based approach to NIL Entity Linking},
  journal = {Journal of Biomedical Informatics},
  volume = {132},
  pages = {104137},
  year = {2022},
  issn = {1532-0464},
  doi = {https://doi.org/10.1016/j.jbi.2022.104137},
  url = {https://www.sciencedirect.com/science/article/pii/S1532046422001526},
  author = {Pedro Ruas and Francisco M. Couto},
}

PubMedBERT fine-tuned on the following datasets:

• CellFinder: entity type "species"
• CRAFT: entity type "NCBITaxon"
• MLEE:entity type "organism"
• LINNAEUS (train and dev sets):
• Species-800
• BioNLP11ID: entity type "Organism"
• BioNLP13CG: entity types "Organism", "Organism subdivision"
• miRNA-Test-Corpus: entity type "species"
• Mantra:entity type "DISO"