Details: https://spacy.io/models/ja#ja_core_news_sm
File checksum:
14ff817486950d0c950d0d3e47ca7ba397311afaba8f34797478723d51fb8331
Japanese multi-task CNN trained on UD_Japanese-GSD v2.6-NE. Assigns context-specific token vectors, POS tags, dependency parses and named entities.
| Feature | Description |
|---|---|
| Name | ja_core_news_sm
|
| Version | 2.3.1
|
| spaCy | >=2.3.0,<2.4.0
|
| Model size | 7 MB |
| Pipeline | parser, ner
|
| Vectors | 0 keys, 0 unique vectors (0 dimensions) |
| Sources | UD_Japanese-GSD v2.6 (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 v2.6-NE (Megagon Labs Tokyo) SudachiPy (Works Applications) SudachiDict (Works Applications) |
| License | CC BY-SA 4.0
|
| Author | Explosion and Megagon Labs Tokyo |
Label Scheme
| Component | Labels |
|---|---|
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 |
|---|---|
LAS
| 86.87 |
UAS
| 88.68 |
TOKEN_ACC
| 97.67 |
ENTS_F
| 59.93 |
ENTS_P
| 64.88 |
ENTS_R
| 55.68 |
Installation
pip install spacy
python -m spacy download ja_core_news_sm