Filename: cord-ner-space

• Current status: NER model in effect

What it identifies:

• 9 new entity types related to COVID-19 studies
  • Coronavirus: COVID-19, SARS-COV, MERS-COV, etc.
  • Viral Protein: Hemagglutinin, GP120, etc.
  • Livestock: cattle, sheep, pig, etc.
  • Wildlife: bats, pangolins, African green monkey, etc
  • Evolution: genetic drift, natural selection, mutation rate, etc
  • Physical Science: atomic charge, Amber force fields, Van der Waals force, etc.
  • Substrate: blood, sputum, urine, etc.
  • Material: copper, stainless steel, plastic, etc.
  • Immune Response: adaptive immune response, cell mediated immunity, innate immunity, etc.

Of note, the original authors' model also include the following, though it's not currently implemented by the task-ties team

• 18 general entity types (Spacy)
• 18 biomedical entity types (SciSpacy)
• 127 biomedical entity types (UMLS as knowledge base)

Inputs

• Annotations & (1) model from the original authors

Outputs

• SpaCy model for prediction of 9 general coronavirus-related entity types