README.md

metadata

tags:
  - spacy
  - token-classification
language:
  - en
license: mit
model-index:
  - name: en_core_web_md
    results:
      - task:
          name: NER
          type: token-classification
        metrics:
          - name: NER Precision
            type: precision
            value: 0.853733758
          - name: NER Recall
            type: recall
            value: 0.8456530449
          - name: NER F Score
            type: f_score
            value: 0.8496741892
      - task:
          name: POS
          type: token-classification
        metrics:
          - name: POS Accuracy
            type: accuracy
            value: 0.9727831973
      - task:
          name: SENTER
          type: token-classification
        metrics:
          - name: SENTER Precision
            type: precision
            value: 0.9049104721
          - name: SENTER Recall
            type: recall
            value: 0.8801372122
          - name: SENTER F Score
            type: f_score
            value: 0.8923519379
      - task:
          name: UNLABELED_DEPENDENCIES
          type: token-classification
        metrics:
          - name: Unlabeled Dependencies Accuracy
            type: accuracy
            value: 0.9186878782
      - task:
          name: LABELED_DEPENDENCIES
          type: token-classification
        metrics:
          - name: Labeled Dependencies Accuracy
            type: accuracy
            value: 0.9186878782

Details: https://spacy.io/models/en#en_core_web_md

English pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter, ner, attribute_ruler, lemmatizer.

Feature	Description
Name	en_core_web_md
Version	3.1.0
spaCy	>=3.1.0,<3.2.0
Default Pipeline	tok2vec, tagger, parser, attribute_ruler, lemmatizer, ner
Components	tok2vec, tagger, parser, senter, attribute_ruler, lemmatizer, ner
Vectors	684830 keys, 20000 unique vectors (300 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) GloVe Common Crawl (Jeffrey Pennington, Richard Socher, and Christopher D. Manning)
License	MIT
Author	Explosion

Accuracy

Type	Score
TOKEN_ACC	99.93
TAG_ACC	97.28
DEP_UAS	91.87
DEP_LAS	90.05
ENTS_P	85.37
ENTS_R	84.57
ENTS_F	84.97
SENTS_P	90.49
SENTS_R	88.01
SENTS_F	89.24