Hugging Face's logo

spacy
/
zh_core_web_trf

Token Classification
spaCy
Chinese
Eval Results
Model card Files Community
zh_core_web_trf / README.md
osanseviero's picture
osanseviero HF staff
Update spaCy pipeline
5c423e0
preview code
|
raw history blame
No virus
3.71 kB
metadata
tags:
  - spacy
  - token-classification
language:
  - zh
license: mit
model-index:
  - name: zh_core_web_trf
    results:
      - task:
          name: NER
          type: token-classification
        metrics:
          - name: NER Precision
            type: precision
            value: 0.746365105
          - name: NER Recall
            type: recall
            value: 0.7615384615
          - name: NER F Score
            type: f_score
            value: 0.7538754419
      - task:
          name: POS
          type: token-classification
        metrics:
          - name: POS Accuracy
            type: accuracy
            value: 0.9247167985
      - task:
          name: SENTER
          type: token-classification
        metrics:
          - name: SENTER Precision
            type: precision
            value: 0.7110739502
          - name: SENTER Recall
            type: recall
            value: 0.6370900616
          - name: SENTER F Score
            type: f_score
            value: 0.67205198
      - task:
          name: UNLABELED_DEPENDENCIES
          type: token-classification
        metrics:
          - name: Unlabeled Dependencies Accuracy
            type: accuracy
            value: 0.7683558244
      - task:
          name: LABELED_DEPENDENCIES
          type: token-classification
        metrics:
          - name: Labeled Dependencies Accuracy
            type: accuracy
            value: 0.7683558244

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

Chinese transformer pipeline (bert-base-chinese). Components: transformer, tagger, parser, ner, attribute_ruler.

Feature Description
Name zh_core_web_trf
Version 3.2.0
spaCy >=3.2.0,<3.3.0
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 97.88
TOKEN_P 94.58
TOKEN_R 91.36
TOKEN_F 92.94
TAG_ACC 92.47
SENTS_P 71.11
SENTS_R 63.71
SENTS_F 67.21
DEP_UAS 76.84
DEP_LAS 73.07
ENTS_P 74.64
ENTS_R 76.15
ENTS_F 75.39