Details: https://github.com/ipipan/spacy-pl-trf
Polish transformer pipeline (herbert-base-cased). Components: transformer, tagger, parser, ner, morfeusz.
Feature | Description |
---|---|
Name | pl_nask |
Version | 0.0.7 |
spaCy | >=3.5.0,<3.6.0 |
Default Pipeline | transformer , tagger , morphologizer , parser , ner , morfeusz |
Components | transformer , tagger , morphologizer , parser , ner , morfeusz |
Vectors | 0 keys, 0 unique vectors (0 dimensions) |
Sources | Morfeusz2 2-clauseBSD License NKJP1M CC-BY NKJP1MUD GNU GPL v.3 Herbert-base-cased CC-BY PDB CC BY-NC-SA 4.0 |
| License | GNU GPL 3.0
|
| Author | Ryszard Tuora ICS PAS |
Label Scheme
View label scheme
Component | Labels |
---|---|
parser |
ROOT , acl , acl:relcl , advcl , advcl:cmpr , advcl:relcl , advmod , advmod:arg , advmod:emph , advmod:neg , amod , amod:flat , appos , aux , aux:cnd , aux:imp , aux:pass , case , cc , cc:preconj , ccomp , ccomp:cleft , ccomp:obj , conj , cop , csubj , dep , det , det:numgov , det:nummod , det:poss , discourse:intj , expl:pv , fixed , flat , flat:foreign , iobj , list , mark , nmod , nmod:arg , nmod:flat , nmod:poss , nsubj , nsubj:pass , nummod , nummod:flat , nummod:gov , obj , obl , obl:agent , obl:arg , obl:cmpr , obl:orphan , orphan , parataxis:insert , parataxis:obj , punct , vocative , xcomp , xcomp:cleft , xcomp:pred , xcomp:subj |
ner |
DATE , GEOGNAME , ORGNAME , PERSNAME , PLACENAME , TIME |
Accuracy
Type | Score |
---|---|
TAG_ACC |
96.26 |
POS_ACC |
98.18 |
MORPH_ACC |
96.61 |
SENTS_P |
99.13 |
SENTS_R |
99.24 |
SENTS_F |
99.19 |
DEP_UAS |
92.91 |
DEP_LAS |
87.66 |
ENTS_P |
90.92 |
ENTS_R |
90.72 |
ENTS_F |
90.82 |
- Downloads last month
- 22
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.
Evaluation results
- NER Precisionself-reported0.909
- NER Recallself-reported0.907
- NER F Scoreself-reported0.908
- TAG (XPOS) Accuracyself-reported0.9626419163,
- Unlabeled Attachment Score (UAS)self-reported0.929
- Labeled Attachment Score (LAS)self-reported0.877
- Sentences F-Scoreself-reported0.992