README.md · spacy/ja_core_news

metadata

tags:
  - spacy
  - token-classification
language:
  - ja
license: cc-by-sa-4.0
model-index:
  - name: ja_core_news_lg
    results:
      - task:
          name: NER
          type: token-classification
        metrics:
          - name: NER Precision
            type: precision
            value: 0.7388362652
          - name: NER Recall
            type: recall
            value: 0.6867924528
          - name: NER F Score
            type: f_score
            value: 0.7118644068
      - task:
          name: TAG
          type: token-classification
        metrics:
          - name: TAG (XPOS) Accuracy
            type: accuracy
            value: 0.9713282143
      - task:
          name: POS
          type: token-classification
        metrics:
          - name: POS (UPOS) Accuracy
            type: accuracy
            value: 0.9742268041
      - task:
          name: MORPH
          type: token-classification
        metrics:
          - name: Morph (UFeats) Accuracy
            type: accuracy
            value: 0
      - task:
          name: LEMMA
          type: token-classification
        metrics:
          - name: Lemma Accuracy
            type: accuracy
            value: 0.9670499959
      - task:
          name: UNLABELED_DEPENDENCIES
          type: token-classification
        metrics:
          - name: Unlabeled Attachment Score (UAS)
            type: f_score
            value: 0.9212481426
      - task:
          name: LABELED_DEPENDENCIES
          type: token-classification
        metrics:
          - name: Labeled Attachment Score (LAS)
            type: f_score
            value: 0.9089518668
      - task:
          name: SENTS
          type: token-classification
        metrics:
          - name: Sentences F-Score
            type: f_score
            value: 0.9658536585

Details: https://spacy.io/models/ja#ja_core_news_lg

Japanese pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler.

Feature	Description
Name	`ja_core_news_lg`
Version	`3.7.0`
spaCy	`>=3.7.0,<3.8.0`
Default Pipeline	`tok2vec`, `morphologizer`, `parser`, `attribute_ruler`, `ner`
Components	`tok2vec`, `morphologizer`, `parser`, `senter`, `attribute_ruler`, `ner`
Vectors	480443 keys, 480443 unique vectors (300 dimensions)
Sources	UD Japanese GSD v2.8 (Omura, Mai; Miyao, Yusuke; Kanayama, Hiroshi; Matsuda, Hiroshi; Wakasa, Aya; Yamashita, Kayo; Asahara, Masayuki; Tanaka, Takaaki; Murawaki, Yugo; Matsumoto, Yuji; Mori, Shinsuke; Uematsu, Sumire; McDonald, Ryan; Nivre, Joakim; Zeman, Daniel) UD Japanese GSD v2.8 NER (Megagon Labs Tokyo) chiVe: Japanese Word Embedding with Sudachi & NWJC (chive-1.1-mc90-500k) (Works Applications)
License	`CC BY-SA 4.0`
Author	Explosion

Label Scheme

View label scheme (65 labels for 3 components)

Component	Labels
`morphologizer`	`POS=NOUN`, `POS=ADP`, `POS=VERB`, `POS=SCONJ`, `POS=AUX`, `POS=PUNCT`, `POS=PART`, `POS=DET`, `POS=NUM`, `POS=ADV`, `POS=PRON`, `POS=ADJ`, `POS=PROPN`, `POS=CCONJ`, `POS=SYM`, `POS=NOUN\|Polarity=Neg`, `POS=AUX\|Polarity=Neg`, `POS=SPACE`, `POS=INTJ`, `POS=SCONJ\|Polarity=Neg`
`parser`	`ROOT`, `acl`, `advcl`, `advmod`, `amod`, `aux`, `case`, `cc`, `ccomp`, `compound`, `cop`, `csubj`, `dep`, `det`, `dislocated`, `fixed`, `mark`, `nmod`, `nsubj`, `nummod`, `obj`, `obl`, `punct`
`ner`	`CARDINAL`, `DATE`, `EVENT`, `FAC`, `GPE`, `LANGUAGE`, `LAW`, `LOC`, `MONEY`, `MOVEMENT`, `NORP`, `ORDINAL`, `ORG`, `PERCENT`, `PERSON`, `PET_NAME`, `PHONE`, `PRODUCT`, `QUANTITY`, `TIME`, `TITLE_AFFIX`, `WORK_OF_ART`

Accuracy

Type	Score
`TOKEN_ACC`	99.37
`TOKEN_P`	97.64
`TOKEN_R`	97.88
`TOKEN_F`	97.76
`POS_ACC`	97.42
`MORPH_ACC`	0.00
`MORPH_MICRO_P`	34.01
`MORPH_MICRO_R`	98.04
`MORPH_MICRO_F`	50.51
`SENTS_P`	95.56
`SENTS_R`	97.63
`SENTS_F`	96.59
`DEP_UAS`	92.12
`DEP_LAS`	90.90
`TAG_ACC`	97.13
`LEMMA_ACC`	96.70
`ENTS_P`	73.88
`ENTS_R`	68.68
`ENTS_F`	71.19