---
language:
- en
pipeline_tag: token-classification
license: apache-2.0
---

Named Entity Recognition (NER) model to recognize chemical 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](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) fine-tuned on the following datasets:

- [Chemdner patents CEMP corpus](https://biocreative.bioinformatics.udel.edu/resources/corpora/chemdner-patents-cemp-corpus/) (train, dev, test sets)
- [DDI corpus](https://github.com/isegura/DDICorpus) (train, dev, test sets): entity types "GROUP", "DRUG", "DRUG_N"
- [GREC Corpus](http://www.nactem.ac.uk/GREC/standoff.php) (train, dev, test sets): entity type  "organic_compounds"
- [MLEE](http://nactem.ac.uk/MLEE/) (train, dev, test sets): entity type "Drug or compound"
- [NLM-CHEM](https://ftp.ncbi.nlm.nih.gov/pub/lu/NLMChem/) (train, dev, test sets)
- [CHEMDNER](https://biocreative.bioinformatics.udel.edu/resources/) (train, dev, test sets)
- [Chebi Corpus](http://www.nactem.ac.uk/chebi/) (train, dev, test sets): entity types "Metabolite", "Chemical"
- [PHAEDRA](http://www.nactem.ac.uk/PHAEDRA/) (train, dev, test sets): entity type "Pharmalogical_substance"
- [Chemprot](https://biocreative.bioinformatics.udel.edu/tasks/biocreative-vi/track-5/) (train, dev, test sets)
- [PGx Corpus](https://github.com/practikpharma/PGxCorpus) (train, dev, test sets): entity type "Chemical"
- [BioNLP11ID](https://github.com/cambridgeltl/MTL-Bioinformatics-2016/tree/master/data/BioNLP11ID-chem-IOB) (train, dev, test sets): entity type "Chemical"
- [BioNLP13CG]() (train, dev, test sets): entity type "Chemical"
- [BC4CHEMD](https://github.com/cambridgeltl/MTL-Bioinformatics-2016/tree/master/data/BC4CHEMD) (train, dev, test sets)
- [CRAFT corpus](https://github.com/UCDenver-ccp/CRAFT/tree/master/concept-annotation) (train, dev, test sets): entity type "ChEBI"
- [BC5CDR]() (train, dev, test sets): entity type "Chemical"