id_core_news_sm / README.md
firqaaa's picture
Update spaCy pipeline
b8a2277 verified
metadata
tags:
  - spacy
  - token-classification
language:
  - id
model-index:
  - name: id_core_news_sm
    results:
      - task:
          name: NER
          type: token-classification
        metrics:
          - name: NER Precision
            type: precision
            value: 0.6744068652
          - name: NER Recall
            type: recall
            value: 0.7046413502
          - name: NER F Score
            type: f_score
            value: 0.6891926747
      - task:
          name: TAG
          type: token-classification
        metrics:
          - name: TAG (XPOS) Accuracy
            type: accuracy
            value: 0.9230464416
      - task:
          name: POS
          type: token-classification
        metrics:
          - name: POS (UPOS) Accuracy
            type: accuracy
            value: 0.9235158913
      - task:
          name: MORPH
          type: token-classification
        metrics:
          - name: Morph (UFeats) Accuracy
            type: accuracy
            value: 0.9448694067
      - task:
          name: LEMMA
          type: token-classification
        metrics:
          - name: Lemma Accuracy
            type: accuracy
            value: 0.970604548
      - task:
          name: UNLABELED_DEPENDENCIES
          type: token-classification
        metrics:
          - name: Unlabeled Attachment Score (UAS)
            type: f_score
            value: 0.8197906398
      - task:
          name: LABELED_DEPENDENCIES
          type: token-classification
        metrics:
          - name: Labeled Attachment Score (LAS)
            type: f_score
            value: 0.7328201277
      - task:
          name: SENTS
          type: token-classification
        metrics:
          - name: Sentences F-Score
            type: f_score
            value: 0.859929078
Feature Description
Name id_core_news_sm
Version 0.0.4
spaCy >=3.7.0,<3.8.0
Default Pipeline tok2vec, ner, tagger, morphologizer, trainable_lemmatizer, parser
Components tok2vec, ner, tagger, morphologizer, trainable_lemmatizer, parser
Vectors 0 keys, 0 unique vectors (0 dimensions)
Sources n/a
License n/a
Author n/a

Label Scheme

View label scheme (321 labels for 4 components)
Component Labels
ner CARDINAL, DATE, EVENT, FAC, GPE, LANGUAGE, LAW, LOC, MONEY, NORP, ORDINAL, ORG, PERCENT, PERSON, PRODUCT, QUANTITY, TIME, WORK_OF_ART
tagger APP, ASP, ASP+PS2, ASP+PS3, ASP+T--, ASS, ASS+PS3, B--, B--+PS3, B--+T--, CC-, CC-+PS3, CC-+T--, CD-, CD-+PS3, CO-, CO-+PS3, D--, D--+PS2, D--+PS3, D--+T--, F--, F--+PS1, F--+PS2, F--+PS3, F--+T--, G--, G--+PS3, G--+T--, H--, H--+T--, I--, M--, M--+PS3, M--+T--, NOUN, NPD, NPD+PS2, NPD+PS3, NSD, NSD+PS1, NSD+PS2, NSD+PS3, NSD+T--, NSF, NSM, NSM+PS3, NUM, O--, PP1, PP1+T--, PP2, PP3, PP3+T--, PROPN, PS1, PS1+VSA, PS1+VSA+T--, PS2, PS2+VSA, PS3, PUNCT, R--, R--+PS1, R--+PS2, R--+PS3, S--, S--+PS3, T--, VERB, VPA, VSA, VSA+PS1, VSA+PS2, VSA+PS3, VSA+T--, VSP, VSP+PS3, VSP+T--, W--, W--+T--, X, X--, Z--
morphologizer POS=PROPN, POS=AUX, POS=DET|PronType=Ind, Number=Sing|POS=NOUN, POS=PRON|PronType=Rel, Number=Sing|POS=VERB|Voice=Pass, POS=ADP, POS=PUNCT, Number=Sing|POS=PROPN, POS=NOUN, POS=ADV, POS=CCONJ, Number=Sing|POS=VERB|Voice=Act, POS=VERB, POS=DET|PronType=Tot, Number=Sing|Number[psor]=Sing|POS=NOUN|Person[psor]=3, POS=SCONJ, Number=Plur|POS=PRON|Person=3|PronType=Prs, POS=DET|PronType=Dem, NumType=Card|POS=NUM, Degree=Pos|Number=Sing|POS=NOUN, Degree=Pos|Number=Sing|POS=ADJ, NumType=Card|POS=DET|PronType=Ind, Degree=Pos|Number=Sing|POS=ADP, Number[psor]=Sing|POS=NOUN|Person[psor]=3, Number=Sing|POS=VERB, POS=PRON|PronType=Int, Number=Sing|POS=ADV|Voice=Act, Number=Sing|Number[psor]=Sing|POS=VERB|Person[psor]=3|Voice=Act, Number=Sing|POS=ADP|Voice=Act, POS=ADJ, Number[psor]=Sing|POS=ADP|Person[psor]=3, Degree=Pos|Number=Sing|POS=DET, Degree=Pos|Number=Sing|POS=VERB, POS=PRON|PronType=Dem, POS=PART|Polarity=Neg, Degree=Pos|Number=Sing|Number[psor]=Sing|POS=NOUN|Person[psor]=3, Number=Sing|POS=PRON|Person=1|Polite=Form|PronType=Prs, Number=Sing|POS=ADJ, Number=Sing|POS=PRON|Person=3|PronType=Prs, POS=SYM, POS=ADV|PronType=Int, Clusivity=In|Number=Plur|POS=PRON|Person=1|PronType=Prs, Number=Sing|POS=ADJ|Voice=Act, Degree=Pos|Number=Sing|POS=PROPN, Degree=Pos|Number=Sing|POS=ADV, Number=Sing|Number[psor]=Sing|POS=VERB|Person[psor]=3|Voice=Pass, Number=Sing|Number[psor]=Sing|POS=NOUN|Person[psor]=3|Voice=Act, Number=Sing|POS=PROPN|Voice=Act, Number=Sing|POS=NOUN|Voice=Act, POS=DET, Number=Sing|POS=DET|Voice=Act, NumType=Card|POS=PRON|PronType=Ind, Number=Sing|Number[psor]=Sing|POS=ADV|Person[psor]=3, Number=Sing|POS=DET, Number=Sing|POS=ADJ|Voice=Pass, POS=CCONJ|PronType=Dem, Number=Sing|POS=ADP, Number=Sing|POS=ADV, Number=Sing|POS=PRON|Person=2|Polite=Infm|PronType=Prs, Number[psor]=Sing|POS=NOUN|Person[psor]=2, Number=Plur|Number[psor]=Sing|POS=NOUN|Person[psor]=2, Number=Sing|POS=PRON, POS=PRON, NumType=Card|POS=ADV|PronType=Ind, NumType=Card|Number[psor]=Sing|POS=NUM|Person[psor]=3, Number=Sing|POS=PRON|Person=3|Polite=Form|PronType=Prs, POS=DET|PronType=Int, Number=Sing|Number[psor]=Sing|POS=PROPN|Person[psor]=3, Number=Sing|Number[psor]=Sing|POS=PROPN|Person[psor]=1, Degree=Pos|Number=Sing|POS=SCONJ, POS=PRON|PronType=Ind, Number=Sing|Number[psor]=Sing|POS=NOUN|Person[psor]=3|Voice=Pass, POS=VERB|PronType=Ind, Degree=Pos|Number=Sing|Number[psor]=Sing|POS=ADJ|Person[psor]=3, Number=Sing|POS=SCONJ, Degree=Sup|Number=Sing|Number[psor]=Sing|POS=ADJ|Person[psor]=3, Degree=Pos|Number=Sing|Number[psor]=Sing|POS=ADP|Person[psor]=3, Number=Plur|Number[psor]=Sing|POS=NOUN|Person[psor]=3, Number=Plur|POS=NOUN, POS=ADV|PronType=Dem, Number=Sing|POS=VERB|Person=1|Voice=Act, Degree=Sup|Number=Sing|POS=ADJ, Number=Sing|POS=ADP|Voice=Pass, Number[psor]=Sing|POS=PART|Person[psor]=3, Number=Sing|POS=NOUN|Voice=Pass, Degree=Pos|Number=Sing|Number[psor]=Sing|POS=CCONJ|Person[psor]=3, POS=PART, Number=Sing|Number[psor]=Sing|POS=PART|Person[psor]=3|Voice=Pass, Degree=Sup|Number=Sing|POS=ADV, Number=Sing|POS=PRON|Voice=Act, Number=Sing|Number[psor]=Sing|POS=PROPN|Person[psor]=3|Voice=Act, Gender=Masc|Number=Sing|POS=PROPN, Number[psor]=Sing|POS=PRON|Person[psor]=3|PronType=Tot, Degree=Pos|Number=Sing|POS=X, POS=PRON|PronType=Tot, Degree=Pos|Number=Sing|Number[psor]=Sing|POS=ADV|Person[psor]=3, Degree=Pos|Number=Sing|Number[psor]=Sing|POS=VERB|Person[psor]=3, Number=Sing|Number[psor]=Sing|POS=ADP|Person[psor]=3, Number=Sing|Number[psor]=Sing|POS=NOUN|Person[psor]=2, POS=SCONJ|PronType=Int, Number=Plur|POS=PRON|Person=2|PronType=Prs, Number=Sing|Number[psor]=Sing|POS=VERB|Person[psor]=1|Voice=Act, Number[psor]=Sing|POS=DET|Person[psor]=3, Number=Sing|Number[psor]=Sing|POS=PRON|Person[psor]=3, Clusivity=Ex|Number=Plur|POS=PRON|Person=1|PronType=Prs, Number=Plur|POS=VERB|Voice=Act, Number=Sing|Number[psor]=Sing|POS=ADV|Person[psor]=3|Voice=Act, Degree=Pos|Number=Sing|POS=NOUN|Polarity=Neg, POS=X, Number[psor]=Sing|POS=ADJ|Person[psor]=3, Number=Sing|Number[psor]=Sing|POS=VERB|Person[psor]=3, Number=Sing|POS=PRON|Person=2|Polite=Form|PronType=Prs, Number=Sing|POS=PRON|Person=1|Polite=Infm|PronType=Prs, Number=Sing|POS=PROPN|Voice=Pass, POS=ADV|Polarity=Neg, NumType=Card|Number=Sing|POS=NUM, Number[psor]=Sing|POS=ADV|Person[psor]=2, Number[psor]=Sing|POS=ADV|Person[psor]=3, Degree=Sup|Number=Sing|POS=PROPN, POS=PROPN|Polarity=Neg, Number=Sing|Number[psor]=Sing|POS=VERB|Person[psor]=2|Voice=Act, Number=Sing|POS=PROPN|Person=1|Voice=Act, POS=SCONJ|PronType=Dem, Number=Sing|Number[psor]=Sing|POS=ADV|Person[psor]=2|Voice=Act, Number=Sing|POS=CCONJ, Degree=Sup|Number=Sing|POS=VERB, Number=Sing|Number[psor]=Sing|POS=ADJ|Person[psor]=3, Number=Sing|Number[psor]=Sing|POS=ADJ|Person[psor]=3|Voice=Act, Degree=Pos|Number=Sing|POS=PRON, Number=Sing|POS=ADV|Voice=Pass, Number[psor]=Sing|POS=ADP|Person[psor]=2, Number=Sing|POS=SYM, POS=ADJ|Polarity=Neg, Degree=Pos|NumType=Card|Number=Sing|POS=NUM, Number=Sing|Number[psor]=Sing|POS=SCONJ|Person[psor]=3, Degree=Pos|Number=Sing|POS=CCONJ, Number[psor]=Sing|POS=NOUN|Person[psor]=1, Number=Sing|POS=CCONJ|Voice=Act, Gender=Masc|Number=Sing|POS=NOUN, Number=Sing|Number[psor]=Sing|POS=ADP|Person[psor]=3|Voice=Pass, Gender=Fem|Number=Sing|POS=PROPN, POS=VERB|PronType=Dem, Number=Sing|POS=PRON|Person=2|PronType=Prs, Gender=Masc|Number=Sing|Number[psor]=Sing|POS=NOUN|Person[psor]=3, Number=Sing|POS=PART|Voice=Act, Degree=Sup|Number=Sing|Number[psor]=Sing|POS=NOUN|Person[psor]=3, POS=ADP|PronType=Int, Number[psor]=Sing|POS=VERB|Person[psor]=3, Number[psor]=Sing|POS=PRON|Person[psor]=3|PronType=Rel, Degree=Pos|Number=Sing|POS=AUX, Number=Sing|Number[psor]=Sing|POS=NOUN|Person[psor]=1, Number=Sing|POS=SCONJ|Voice=Pass, Degree=Sup|Number=Sing|POS=ADP, Number=Sing|POS=SCONJ|Voice=Act, NumType=Card|POS=DET|PronType=Int, Degree=Pos|Number=Sing|POS=PART|Polarity=Neg, Degree=Sup|Number=Sing|POS=SCONJ, Number=Sing|Number[psor]=Sing|POS=NOUN|Person[psor]=1|Voice=Act, Number=Plur|POS=ADJ, POS=VERB|PronType=Int, Number=Sing|POS=VERB|Person=2|Voice=Act, Degree=Pos|Number=Sing|Number[psor]=Sing|POS=ADJ|Person[psor]=2, Gender=Masc|Number=Sing|POS=ADJ, Number[psor]=Sing|POS=ADV|Person[psor]=3|PronType=Tot, POS=DET|PronType=Rel, Number=Sing|POS=NOUN|Polarity=Neg, Number=Sing|Number[psor]=Sing|POS=PROPN|Person[psor]=2, NumType=Card|Number=Sing|POS=NUM|Voice=Act, Degree=Pos|Number=Plur|POS=ADJ, Number[psor]=Sing|POS=DET|Person[psor]=3|PronType=Tot, Number[psor]=Sing|POS=PROPN|Person[psor]=1, Gender=Fem|Number=Sing|POS=NOUN, Number=Sing|POS=VERB|Person=1, Degree=Pos|Number=Sing|Number[psor]=Sing|POS=PROPN|Person[psor]=3, NumType=Card|Number[psor]=Sing|POS=DET|Person[psor]=3|PronType=Ind, POS=ADV|PronType=Tot, Degree=Pos|Number=Plur|POS=ADV, Number=Plur|POS=ADV|Voice=Act, POS=CCONJ|PronType=Int, Degree=Pos|Number=Sing|POS=PART, Number[psor]=Sing|POS=PRON|Person[psor]=2, Number=Plur|POS=VERB, Number=Sing|Number[psor]=Sing|POS=ADJ|Person[psor]=3|Voice=Pass, Degree=Pos|Number=Sing|POS=PUNCT, Number[psor]=Sing|POS=ADP|Person[psor]=1, Degree=Sup|Number=Sing|POS=NOUN, Number[psor]=Sing|POS=PART|Person[psor]=3|Polarity=Neg, Number=Sing|Number[psor]=Sing|POS=ADP|Person[psor]=3|Voice=Act, POS=NOUN|Polarity=Neg, Number[psor]=Sing|POS=PROPN|Person[psor]=2, Number=Sing|Number[psor]=Sing|POS=NOUN|Person[psor]=2|Voice=Act
parser ROOT, acl, advcl, advmod, amod, appos, case, cc, ccomp, compound, compound:plur, conj, cop, dep, det, fixed, flat, mark, nmod, nsubj, nsubj:pass, nummod, obj, obl, parataxis, punct, xcomp

Accuracy

Type Score
ENTS_F 68.92
ENTS_P 67.44
ENTS_R 70.46
TAG_ACC 92.30
POS_ACC 92.35
MORPH_ACC 94.49
LEMMA_ACC 97.06
DEP_UAS 81.98
DEP_LAS 73.28
SENTS_P 85.24
SENTS_R 86.76
SENTS_F 85.99
TOK2VEC_LOSS 984087.67
NER_LOSS 123734.71
TAGGER_LOSS 65883.76
MORPHOLOGIZER_LOSS 200589.63
TRAINABLE_LEMMATIZER_LOSS 23717.64
PARSER_LOSS 1145740.96