Instructions to use surrey-nlp/en_abbreviation_detection_roberta_lar with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- spaCy
How to use surrey-nlp/en_abbreviation_detection_roberta_lar with spaCy:
!pip install https://huggingface.co/surrey-nlp/en_abbreviation_detection_roberta_lar/resolve/main/en_abbreviation_detection_roberta_lar-any-py3-none-any.whl # Using spacy.load(). import spacy nlp = spacy.load("en_abbreviation_detection_roberta_lar") # Importing as module. import en_abbreviation_detection_roberta_lar nlp = en_abbreviation_detection_roberta_lar.load() - Notebooks
- Google Colab
- Kaggle
| Feature | Description |
|---|---|
| Name | en_abbreviation_detection_roberta_lar |
| Version | 0.0.1 |
| spaCy | >=3.2.1,<3.3.0 |
| Default Pipeline | transformer, abbreviationDetection |
| Components | transformer, abbreviationDetection |
| Vectors | 0 keys, 0 unique vectors (0 dimensions) |
| Sources | PLOSDataset-LREC22-Submitted |
| License | cc-by-sa-4.0 |
| Author | Diptesh Kanojia |
Label Scheme
View label scheme (3 labels for 1 components)
| Component | Labels |
|---|---|
abbreviationDetection |
AC, LF, O |
Accuracy
| Type | Score |
|---|---|
ENTS_F |
95.29 |
ENTS_P |
96.12 |
ENTS_R |
94.47 |
TRANSFORMER_LOSS |
287952.16 |
NER_LOSS |
608954.79 |
- Downloads last month
- 4
Evaluation results
- Precisionself-reported0.961
- Recallself-reported0.945
- F Scoreself-reported0.953