Research Spotlight
Collection
Research Spotlight is a modular workflow written in Python for converting research publications into an ontology-driven scholarly knowledge graph. • 3 items • Updated
A Named Entity Recognition (NER) model specialized in detecting research goals or objectives from scholarly publications.
| Feature | Description |
|---|---|
| Name | en_deberta_v3_base_ner_goal |
| Version | 0.1.0 |
| spaCy | >=3.8.7,<3.9.0 |
| Default Pipeline | transformer, ner |
| Components | transformer, ner |
| License | MIT |
Label Scheme
View label scheme (1 labels for 1 components)
| Component | Labels |
|---|---|
ner |
GOAL |
Accuracy
| Type | Score |
|---|---|
ENTS_F |
74.41 |
ENTS_P |
72.34 |
ENTS_R |
76.61 |
- Downloads last month
- 42
Model tree for NikosKprl/en_deberta_v3_base_ner_goal
Base model
microsoft/deberta-v3-baseCollection including NikosKprl/en_deberta_v3_base_ner_goal
Evaluation results
- NER Precisionself-reported0.723
- NER Recallself-reported0.766
- NER F Scoreself-reported0.744