en_skillner / README.md
lizgzil's picture
Update spaCy pipeline
ce96244 verified
metadata
tags:
  - spacy
  - token-classification
language:
  - en
license: mit
model-index:
  - name: en_skillner
    results:
      - task:
          name: NER
          type: token-classification
        metrics:
          - name: NER Precision
            type: precision
            value: 0.5919354839
          - name: NER Recall
            type: recall
            value: 0.5758368201
          - name: NER F Score
            type: f_score
            value: 0.5837751856

A Named Entity Recognition (NER) model to extract SKILL, EXPERIENCE and BENEFIT from job adverts.

Feature Description
Name en_skillner
Version 3.7.1
spaCy >=3.7.4,<3.8.0
Default Pipeline tok2vec, tagger, parser, attribute_ruler, lemmatizer, ner
Components tok2vec, tagger, parser, senter, attribute_ruler, lemmatizer, ner
Vectors 514157 keys, 514157 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)
Explosion Vectors (OSCAR 2109 + Wikipedia + OpenSubtitles + WMT News Crawl) (Explosion)
License MIT
Author nestauk

Label Scheme

View label scheme (3 labels for 1 components)
Component Labels
ner SKILL, EXPERIENCE, BENEFIT

Accuracy

Type Score
ENTS_P 59.19
ENTS_R 57.58
ENTS_F 58.38
SKILL_P 72.19
SKILL_R 72.62
SKILL_F 72.40
EXPERIENCE_P 52.14
EXPERIENCE_R 41.48
EXPERIENCE_F 46.20
BENEFIT_P 75.61
BENEFIT_R 46.27
BENEFIT_F 57.41