github explosion/spacy-models en_core_web_trf-3.0.0a1

pre-release3 years ago

Downloads

Details: https://nightly.spacy.io/models/en#en_core_web_trf

File checksum: 64ea841ba29b8ce604af5d67f24e831e03074c72884502a940fddd5df09d7b6d

English transformer pipeline (roberta-base). Components: transformer, tagger, parser, ner, attribute_ruler, lemmatizer.

Feature Description
Name en_core_web_trf
Version 3.0.0a1
spaCy >=3.0.0rc3,<3.1.0
Model size 438 MB
Default Pipeline transformer, tagger, parser, ner, attribute_ruler, lemmatizer
Components transformer, tagger, parser, ner, attribute_ruler, lemmatizer
Vectors 0 keys, 0 unique vectors (0 dimensions)
Sources OntoNotes 5
License MIT
Author Explosion

Label Scheme

View label scheme (112 labels for 3 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, WDT, WP, WP$, WRB, XX, ````
parser ROOT, acl, acomp, advcl, advmod, agent, amod, appos, attr, aux, auxpass, case, cc, ccomp, compound, conj, csubj, csubjpass, dative, dep, det, dobj, expl, intj, mark, meta, neg, nmod, npadvmod, nsubj, nsubjpass, nummod, oprd, parataxis, pcomp, pobj, poss, preconj, predet, prep, prt, punct, quantmod, relcl, xcomp
ner CARDINAL, DATE, EVENT, FAC, GPE, LANGUAGE, LAW, LOC, MONEY, NORP, ORDINAL, ORG, PERCENT, PERSON, PRODUCT, QUANTITY, TIME, WORK_OF_ART

Accuracy

Type Score
TOKEN_ACC 99.93
TAG_ACC 97.82
DEP_UAS 95.23
DEP_LAS 93.87
ENTS_P 90.16
ENTS_R 89.71
ENTS_F 89.93
SENTS_P 94.57
SENTS_R 84.70
SENTS_F 89.37

Installation

pip install spacy-nightly --pre
python -m spacy download en_core_web_trf

Don't miss a new spacy-models release

NewReleases is sending notifications on new releases.