en_healthsea / README.md
edichief's picture
Update spaCy pipeline
cf79cce
|
raw
history blame
1.96 kB
metadata
tags:
  - spacy
  - token-classification
language:
  - en
license: mit
model-index:
  - name: en_healthsea
    results:
      - task:
          name: NER
          type: token-classification
        metrics:
          - name: NER Precision
            type: precision
            value: 0
          - name: NER Recall
            type: recall
            value: 0
          - name: NER F Score
            type: f_score
            value: 0
      - task:
          name: SENTER
          type: token-classification
        metrics:
          - name: SENTER Precision
            type: precision
            value: 1
          - name: SENTER Recall
            type: recall
            value: 1
          - name: SENTER F Score
            type: f_score
            value: 1

Healthsea pipeline for analyzing reviews to supplement products

Feature Description
Name en_healthsea
Version 0.0.1
spaCy >=3.2.0,<3.3.0
Default Pipeline sentencizer, tok2vec, ner, benepar, segmentation, clausecat, aggregation
Components sentencizer, tok2vec, ner, benepar, segmentation, clausecat, aggregation
Vectors 684830 keys, 684830 unique vectors (300 dimensions)
Sources n/a
License MIT
Author Explosion

Label Scheme

View label scheme (6 labels for 2 components)
Component Labels
ner BENEFIT, CONDITION
clausecat POSITIVE, NEUTRAL, NEGATIVE, ANAMNESIS

Accuracy

Type Score
SENTS_F 100.00
SENTS_P 100.00
SENTS_R 100.00
ENTS_F 0.00
ENTS_P 0.00
ENTS_R 0.00
ENTS_PER_TYPE 0.00
CATS_SCORE 74.87
CATS_MICRO_P 82.39
CATS_MICRO_R 80.93
CATS_MICRO_F 81.66
CATS_MACRO_P 78.43
CATS_MACRO_R 72.16
CATS_MACRO_F 74.87
CATS_MACRO_AUC 92.78
CATS_MACRO_AUC_PER_TYPE 0.00
CLAUSECAT_LOSS 339.11