bg_news_trf / README.md
sakelariev's picture
Update README.md
4d3695e
|
raw
history blame
2.51 kB
metadata
license: cc-by-nc-sa-3.0
language:
  - bg
metrics:
  - accuracy
library_name: spacy
pipeline_tag: token-classification
model-index:
  - name: bg_news_trf
    results:
      - task:
          name: NER
          type: token-classification
        metrics:
          - name: NER Precision
            type: precision
            value: 0.8890829694
          - name: NER Recall
            type: recall
            value: 0.8886948931
          - name: NER F Score
            type: f_score
            value: 0.8888888889
      - task:
          name: TAG
          type: token-classification
        metrics:
          - name: TAG (XPOS) Accuracy
            type: accuracy
            value: 0.9702076246
      - task:
          name: POS
          type: token-classification
        metrics:
          - name: POS (UPOS) Accuracy
            type: accuracy
            value: 0.9897910505
      - task:
          name: MORPH
          type: token-classification
        metrics:
          - name: Morph (UFeats) Accuracy
            type: accuracy
            value: 0.9764380425
      - task:
          name: LEMMA
          type: token-classification
        metrics:
          - name: Lemma Accuracy
            type: accuracy
            value: 0.9404442198
      - task:
          name: UNLABELED_DEPENDENCIES
          type: token-classification
        metrics:
          - name: Unlabeled Attachment Score (UAS)
            type: f_score
            value: 0.9349327787
      - task:
          name: LABELED_DEPENDENCIES
          type: token-classification
        metrics:
          - name: Labeled Attachment Score (LAS)
            type: f_score
            value: 0.8934417103
      - task:
          name: SENTS
          type: token-classification
        metrics:
          - name: Sentences F-Score
            type: f_score
            value: 0.9241131567
tags:
  - ner
  - named entity recognition
  - spacy
Feature Description
Name bg_news_trf
Version 3.5.4
spaCy >=3.5.4,<3.6.0
Default Pipeline transformer, tagger, morphologizer, parser, trainable_lemmatizer, ner
Components transformer, tagger, morphologizer, parser, trainable_lemmatizer, ner
Vectors 0 keys, 0 unique vectors (0 dimensions)
Sources UD_Bulgarian-BTB (Kiril Simov and Petya Osenova) BERT multilingual base model (uncased) (Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova)
License CC-BY-NC-SA-3.0
Author Ivaylo Sakelariev

Bulgarian transformers pipeline for BGspaCy. Components: tok2vec, tagger, morphologizer, lemmatizer, parser, ner