Feature | Description |
---|---|
Name | en_acnl_roberta_pipeline |
Version | 0.0.1 |
spaCy | >=3.1.3,<3.2.0 |
Default Pipeline | transformer , tagger , parser |
Components | transformer , tagger , parser |
Vectors | 0 keys, 0 unique vectors (0 dimensions) |
Sources | OntoNotes |
License | CC BY-SA 4.0 |
Author | Daniel Vasić |
Label Scheme
View label scheme (87 labels for 2 components)
Component | Labels |
---|---|
tagger |
$ , '' , , , -LRB- , -RRB- , . , : , ADD , AFX , CC , CD , DT , EX , FW , HYPH , IN , JJ , JJR , JJS , LS , MD , NFP , NN , NNP , NNPS , NNS , PDT , POS , PRP , PRP$ , RB , RBR , RBS , RP , SYM , TO , UH , VB , VBD , VBG , VBN , VBP , VBZ , VERB , WDT , WP , WP$ , WRB , XX , ```` |
parser |
ROOT , acl , acomp , advcl , advmod , amod , appos , aux , auxpass , case , cc , ccomp , compound , conj , dative , dep , det , dobj , intj , mark , meta , neg , nmod , npadvmod , nummod , parataxis , pcomp , pobj , poss , preconj , predet , prep , prt , punct , quantmod , relcl , xcomp |
Accuracy
Type | Score |
---|---|
TAG_ACC |
98.05 |
DEP_UAS |
95.98 |
DEP_LAS |
94.83 |
SENTS_P |
93.80 |
SENTS_R |
95.42 |
SENTS_F |
94.61 |
TRANSFORMER_LOSS |
3784861.59 |
TAGGER_LOSS |
698704.80 |
PARSER_LOSS |
5540167.00 |
- Downloads last month
- 6
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Dataset used to train danielvasic/en_acnl_roberta_pipeline
Evaluation results
- POS Accuracyself-reported0.981
- SENTER Precisionself-reported0.938
- SENTER Recallself-reported0.954
- SENTER F Scoreself-reported0.946
- Unlabeled Dependencies Accuracyself-reported0.960
- Labeled Dependencies Accuracyself-reported0.960