Hugging Face's logo

spacy
/
zh_core_web_md

Token Classification
spaCy
Chinese
Eval Results
Model card Files Community
zh_core_web_md / README.md
Adriane Boyd
Update spaCy pipeline
caef619
preview code
|
raw
history blame
3.6 kB
metadata
tags:
  - spacy
  - token-classification
language:
  - zh
license: mit
model-index:
  - name: zh_core_web_md
    results:
      - task:
          name: NER
          type: token-classification
        metrics:
          - name: NER Precision
            type: precision
            value: 0.7221830158
          - name: NER Recall
            type: recall
            value: 0.6747252747
          - name: NER F Score
            type: f_score
            value: 0.6976479945
      - task:
          name: TAG
          type: token-classification
        metrics:
          - name: TAG (XPOS) Accuracy
            type: accuracy
            value: 0.9008590446
      - task:
          name: UNLABELED_DEPENDENCIES
          type: token-classification
        metrics:
          - name: Unlabeled Attachment Score (UAS)
            type: f_score
            value: 0.7039779048
      - task:
          name: LABELED_DEPENDENCIES
          type: token-classification
        metrics:
          - name: Labeled Attachment Score (LAS)
            type: f_score
            value: 0.6517336371
      - task:
          name: SENTS
          type: token-classification
        metrics:
          - name: Sentences F-Score
            type: f_score
            value: 0.7535180869

Details: https://spacy.io/models/zh#zh_core_web_md

Chinese pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter, ner, attribute_ruler.

Feature Description
Name zh_core_web_md
Version 3.4.0
spaCy >=3.4.0,<3.5.0
Default Pipeline tok2vec, tagger, parser, attribute_ruler, ner
Components tok2vec, tagger, parser, senter, attribute_ruler, ner
Vectors 500000 keys, 20000 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)
CoreNLP Universal Dependencies Converter (Stanford NLP Group)
Explosion fastText Vectors (cbow, OSCAR Common Crawl + Wikipedia) (Explosion)
License MIT
Author Explosion

Label Scheme

View label scheme (100 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, _SP
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 97.88
TOKEN_P 94.58
TOKEN_R 91.36
TOKEN_F 92.94
TAG_ACC 90.09
SENTS_P 78.26
SENTS_R 72.65
SENTS_F 75.35
DEP_UAS 70.40
DEP_LAS 65.17
ENTS_P 72.22
ENTS_R 67.47
ENTS_F 69.76