Instructions to use tsantosh7/en_covid19_ner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- spaCy
How to use tsantosh7/en_covid19_ner with spaCy:
!pip install https://huggingface.co/tsantosh7/en_covid19_ner/resolve/main/en_covid19_ner-any-py3-none-any.whl # Using spacy.load(). import spacy nlp = spacy.load("en_covid19_ner") # Importing as module. import en_covid19_ner nlp = en_covid19_ner.load() - Notebooks
- Google Colab
- Kaggle
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
- 4
Evaluation results
- NER Precisionself-reported0.914
- NER Recallself-reported0.936
- NER F Scoreself-reported0.925