en_generic / README.md
magepol's picture
Update spaCy pipeline
f1b2d57 verified
metadata
tags:
  - spacy
  - token-classification
  - text-classification
language:
  - en
model-index:
  - name: en_generic
    results:
      - task:
          name: NER
          type: token-classification
        metrics:
          - name: NER Precision
            type: precision
            value: 0.9421775682
          - name: NER Recall
            type: recall
            value: 0.9493801653
          - name: NER F Score
            type: f_score
            value: 0.9457651539
Feature Description
Name en_generic
Version 0.0.3
spaCy >=3.7.5,<3.8.0
Default Pipeline tok2vec, ner, textcat
Components tok2vec, ner, textcat
Vectors 514157 keys, 514157 unique vectors (300 dimensions)
Sources n/a
License n/a
Author n/a

Label Scheme

View label scheme (29 labels for 2 components)
Component Labels
ner BRAND, COLOR, DISPLAY, GENDER, MATERIAL, MEMORY, MISC, MODEL_IDENTIFIER, PROCESSOR, PRODUCT_TYPE, SEASON, SIZE_MEASUREMENT, STYLE_FIT, TECH_FEATURE
textcat 292, 325, 328, 297, 4745, 267, 204, 207, 2331, 211, 212, 6228, 187, 5598, 2271

Accuracy

Type Score
ENTS_F 94.58
ENTS_P 94.22
ENTS_R 94.94
CATS_SCORE 97.49
CATS_MICRO_P 97.14
CATS_MICRO_R 97.14
CATS_MICRO_F 97.14
CATS_MACRO_P 97.89
CATS_MACRO_R 97.15
CATS_MACRO_F 97.49
CATS_MACRO_AUC 99.84
TOK2VEC_LOSS 22259553.65
NER_LOSS 723658.37
TEXTCAT_LOSS 20.50