ja_core_news_lg-2.3.2
·
1222 commits
to master
since this release
Details: https://spacy.io/models/ja#ja_core_news_lg
File checksum:
749b6484078f802544bc1c6ad15bb5f090bd40f20e4db3ff23c418804879ab5d
Japanese multi-task CNN trained on UD_Japanese-GSD v2.6-NE. Assigns word2vec token vectors, POS tags, dependency parses and named entities.
| Feature | Description |
|---|---|
| Name | ja_core_news_lg |
| Version | 2.3.2 |
| spaCy | >=2.3.0,<2.4.0 |
| Model size | 526 MB |
| Pipeline | 聽parser, ner |
| Vectors | 480443 keys, 480443 unique vectors (300 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) chiVe: Japanese Word Embedding with Sudachi & NWJC (chive-1.1-mc90-500k) (Works Applications) SudachiPy (Works Applications) SudachiDict (Works Applications) |
| License | CC BY-SA 4.0 |
| Author | Explosion and Megagon Labs Tokyo |
Label Scheme
| Component | Labels |
|---|---|
parser |
聽ROOT, acl, advcl, advmod, amod, aux, case, cc, ccomp, compound, cop, csubj, dep, det, dislocated, fixed, mark, nmod, nsubj, nummod, obj, obl, punct |
ner |
聽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 |
聽87.72 |
UAS |
聽89.24 |
TOKEN_ACC |
聽97.67 |
ENTS_F |
聽68.91 |
ENTS_P |
聽71.31 |
ENTS_R |
聽66.67 |
Installation
pip install spacy
python -m spacy download ja_core_news_lg