README.md

metadata

tags:
  - spacy
  - token-classification
language:
  - en
license: mit
model-index:
  - name: en_data_dev_spacy_trf_1
    results:
      - task:
          name: NER
          type: token-classification
        metrics:
          - name: NER Precision
            type: precision
            value: 0.9008293365
          - name: NER Recall
            type: recall
            value: 0.9029947917
          - name: NER F Score
            type: f_score
            value: 0.9019107643
      - task:
          name: TAG
          type: token-classification
        metrics:
          - name: TAG (XPOS) Accuracy
            type: accuracy
            value: 0.9812819818
      - task:
          name: UNLABELED_DEPENDENCIES
          type: token-classification
        metrics:
          - name: Unlabeled Attachment Score (UAS)
            type: f_score
            value: 0.9526219812
      - task:
          name: LABELED_DEPENDENCIES
          type: token-classification
        metrics:
          - name: Labeled Attachment Score (LAS)
            type: f_score
            value: 0.9390746643
      - task:
          name: SENTS
          type: token-classification
        metrics:
          - name: Sentences F-Score
            type: f_score
            value: 0.9011225055

en_data_dev_spacy_trf_1

English spacy model, based on the spacy stock en_core_web_trf transformer-based model, used for regular day to day data engineering.

English transformer pipeline (Transformer(name='roberta-base', piece_encoder='byte-bpe', stride=104, type='roberta', width=768, window=144, vocab_size=50265)). Components: transformer, tagger, parser, ner, attribute_ruler, lemmatizer.

Feature	Description
Name	en_data_dev_spacy_trf_1
Version	3.7.3
spaCy	>=3.7.2,<3.8.0
Default Pipeline	transformer, tagger, parser, attribute_ruler, lemmatizer, ner
Components	transformer, tagger, parser, attribute_ruler, lemmatizer, ner
Vectors	0 keys, 0 unique vectors (0 dimensions)
Sources	OntoNotes 5 (Ralph Weischedel, Martha Palmer, Mitchell Marcus, Eduard Hovy, Sameer Pradhan, Lance Ramshaw, Nianwen Xue, Ann Taylor, Jeff Kaufman, Michelle Franchini, Mohammed El-Bachouti, Robert Belvin, Ann Houston) ClearNLP Constituent-to-Dependency Conversion (Emory University) WordNet 3.0 (Princeton University) roberta-base (Yinhan Liu and Myle Ott and Naman Goyal and Jingfei Du and Mandar Joshi and Danqi Chen and Omer Levy and Mike Lewis and Luke Zettlemoyer and Veselin Stoyanov)
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	99.86
TOKEN_P	99.57
TOKEN_R	99.58
TOKEN_F	99.57
TAG_ACC	98.13
SENTS_P	94.89
SENTS_R	85.79
SENTS_F	90.11
DEP_UAS	95.26
DEP_LAS	93.91
ENTS_P	90.08
ENTS_R	90.30
ENTS_F	90.19