Hugging Face's logo

sigtica
/
zh_data_dev_spacy_trf_1

Token Classification
spaCy
Chinese
Eval Results
Model card Files Community
zh_data_dev_spacy_trf_1 / README.md
emilyllii's picture
emilyllii
Update README.md
2d57c7e verified
preview code
|
raw
history blame contribute delete
3.8 kB
metadata
tags:
  - spacy
  - token-classification
language:
  - zh
license: mit
model-index:
  - name: zh_data_dev_spacy_trf_1
    results:
      - task:
          name: NER
          type: token-classification
        metrics:
          - name: NER Precision
            type: precision
            value: 0.7608897127
          - name: NER Recall
            type: recall
            value: 0.7217582418
          - name: NER F Score
            type: f_score
            value: 0.7408075795
      - task:
          name: TAG
          type: token-classification
        metrics:
          - name: TAG (XPOS) Accuracy
            type: accuracy
            value: 0.9175332527
      - task:
          name: UNLABELED_DEPENDENCIES
          type: token-classification
        metrics:
          - name: Unlabeled Attachment Score (UAS)
            type: f_score
            value: 0.7572203056
      - task:
          name: LABELED_DEPENDENCIES
          type: token-classification
        metrics:
          - name: Labeled Attachment Score (LAS)
            type: f_score
            value: 0.7145288854
      - task:
          name: SENTS
          type: token-classification
        metrics:
          - name: Sentences F-Score
            type: f_score
            value: 0.6920716113

zh_data_dev_spacy_trf_1

Chinese spacy model, based on the spacy stock zh_core_web_trf transformer-based model, used for regular day to day data engineering.

Chinese transformer pipeline (Transformer(name='bert-base-chinese', piece_encoder='bert-wordpiece', stride=152, type='bert', width=768, window=208, vocab_size=21128)). Components: transformer, tagger, parser, ner, attribute_ruler.

Feature Description
Name zh_core_web_trf
Version 3.7.2
spaCy >=3.7.0,<3.8.0
Default Pipeline transformer, tagger, parser, attribute_ruler, ner
Components transformer, tagger, parser, attribute_ruler, ner
Vectors 0 keys, 0 unique vectors (0 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)
CoreNLP Universal Dependencies Converter (Stanford NLP Group)
bert-base-chinese (Hugging Face)
License MIT
Author Explosion

Label Scheme

View label scheme (99 labels for 3 components)
Component Labels
tagger AD, AS, BA, CC, CD, CS, DEC, DEG, DER, DEV, DT, ETC, FW, IJ, INF, JJ, LB, LC, M, MSP, NN, NR, NT, OD, ON, P, PN, PU, SB, SP, URL, VA, VC, VE, VV, X
parser ROOT, acl, advcl:loc, advmod, advmod:dvp, advmod:loc, advmod:rcomp, amod, amod:ordmod, appos, aux:asp, aux:ba, aux:modal, aux:prtmod, auxpass, case, cc, ccomp, compound:nn, compound:vc, conj, cop, dep, det, discourse, dobj, etc, mark, mark:clf, name, neg, nmod, nmod:assmod, nmod:poss, nmod:prep, nmod:range, nmod:tmod, nmod:topic, nsubj, nsubj:xsubj, nsubjpass, nummod, parataxis:prnmod, punct, xcomp
ner CARDINAL, DATE, EVENT, FAC, GPE, LANGUAGE, LAW, LOC, MONEY, NORP, ORDINAL, ORG, PERCENT, PERSON, PRODUCT, QUANTITY, TIME, WORK_OF_ART

Accuracy

Type Score
TOKEN_ACC 95.85
TOKEN_P 94.58
TOKEN_R 91.36
TOKEN_F 92.94
TAG_ACC 91.75
SENTS_P 70.92
SENTS_R 67.57
SENTS_F 69.21
DEP_UAS 75.72
DEP_LAS 71.45
ENTS_P 76.09
ENTS_R 72.18
ENTS_F 74.08