Details: https://nightly.spacy.io/models/ja#ja_core_news_lg
File checksum:
725464e04756204ae741da1a47fcba419cdb74d62a104bbd4851b27039b2437e
Japanese pipeline optimized for CPU. Components: tok2vec, parser, senter, ner, attribute_ruler.
| Feature | Description |
|---|---|
| Name | ja_core_news_lg
|
| Version | 3.0.0a0
|
| spaCy | >=3.0.0a41,<3.1.0
|
| Model size | 536 MB |
| Default Pipeline | tok2vec, parser, ner, attribute_ruler
|
| Components | tok2vec, parser, senter, ner, attribute_ruler
|
| Vectors | 480443 keys, 480443 unique vectors (300 dimensions) |
| Sources | n/a |
| License | All rights reserved
|
| Author | Explosion |
Label Scheme
View label scheme (47 labels for 3 components)
| 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
|
senter
| I, S
|
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 |
|---|---|
TOK
| 99.69 |
TAG
| 97.21 |
POS
| 96.39 |
UAS
| 89.98 |
LAS
| 88.37 |
NER_P
| 74.76 |
NER_R
| 70.37 |
NER_F
| 72.50 |
SENT_P
| 84.40 |
SENT_R
| 89.62 |
SENT_F
| 86.93 |
Installation
pip install spacy-nightly --pre
python -m spacy download ja_core_news_lg