COVID 19 Bio Annotations
The dataset was taken from https://github.com/davidcampos/covid19-corpus
Dataset The dataset was then split into several datasets each one representing one entity. Namely, Disorder, Species, Chemical or Drug, Gene and Protein, Enzyme, Anatomy, Biological Process, Molecular Function, Cellular Component, Pathway and microRNA. Moreover, another dataset is also created with all those aforementioned that are non-overlapping in nature.
Other Dataset Formats The datasets are available in two formats IOB and Spacy's JSONL format.
IOB: https://github.com/tsantosh7/COVID-19-Named-Entity-Recognition/tree/master/Datasets/BIO
SpaCy JSONL: https://github.com/tsantosh7/COVID-19-Named-Entity-Recognition/tree/master/Datasets/SpaCy
Feature | Description |
---|---|
Name | en_covid19_ner |
Version | 0.0.0 |
spaCy | >=3.2.4,<3.3.0 |
Default Pipeline | transformer , ner |
Components | transformer , ner |
Vectors | 0 keys, 0 unique vectors (0 dimensions) |
Sources | n/a |
License | n/a |
Author | Santosh Tirunagai |
Label Scheme
View label scheme (10 labels for 1 components)
Component | Labels |
---|---|
ner |
ANAT , CHED , COMP , DISO , ENZY , FUNC , PATH , PRGE , PROC , SPEC |
Accuracy
Type | Score |
---|---|
ENTS_F |
92.50 |
ENTS_P |
91.40 |
ENTS_R |
93.62 |
TRANSFORMER_LOSS |
311768.03 |
NER_LOSS |
371171.50 |
- Downloads last month
- 0
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Evaluation results
- NER Precisionself-reported0.914
- NER Recallself-reported0.936
- NER F Scoreself-reported0.925