|
--- |
|
tags: |
|
- spacy |
|
- token-classification |
|
language: |
|
- ja |
|
license: CC-BY-SA-4.0 |
|
model-index: |
|
- name: ja_core_news_lg |
|
results: |
|
- tasks: |
|
name: NER |
|
type: token-classification |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.760989011 |
|
- name: Recall |
|
type: recall |
|
value: 0.7075351213 |
|
- name: F Score |
|
type: f_score |
|
value: 0.7332892124 |
|
- tasks: |
|
name: POS |
|
type: token-classification |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9721899386 |
|
- tasks: |
|
name: SENTER |
|
type: token-classification |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.9860557769 |
|
- name: Recall |
|
type: recall |
|
value: 0.9880239521 |
|
- name: F Score |
|
type: f_score |
|
value: 0.9870388833 |
|
- tasks: |
|
name: UNLABELED_DEPENDENCIES |
|
type: token-classification |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9181002928 |
|
- tasks: |
|
name: LABELED_DEPENDENCIES |
|
type: token-classification |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9181002928 |
|
--- |
|
### Details: https://spacy.io/models/ja#ja_core_news_lg |
|
|
|
Japanese pipeline optimized for CPU. Components: tok2vec, parser, senter, ner, attribute_ruler. |
|
|
|
| Feature | Description | |
|
| --- | --- | |
|
| **Name** | `ja_core_news_lg` | |
|
| **Version** | `3.1.0` | |
|
| **spaCy** | `>=3.1.0,<3.2.0` | |
|
| **Default Pipeline** | `tok2vec`, `parser`, `attribute_ruler`, `ner` | |
|
| **Components** | `tok2vec`, `parser`, `senter`, `attribute_ruler`, `ner` | |
|
| **Vectors** | 480443 keys, 480443 unique vectors (300 dimensions) | |
|
| **Sources** | [UD Japanese GSD v2.6](https://github.com/UniversalDependencies/UD_Japanese-GSD) (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)<br />[UD Japanese GSD v2.6 NER](https://github.com/megagonlabs/UD_Japanese-GSD) (Megagon Labs Tokyo)<br />[chiVe: Japanese Word Embedding with Sudachi & NWJC (chive-1.1-mc90-500k)](https://github.com/WorksApplications/chiVe) (Works Applications) | |
|
| **License** | `CC BY-SA 4.0` | |
|
| **Author** | [Explosion](https://explosion.ai) | |
|
|
|
### Label Scheme |
|
|
|
<details> |
|
|
|
<summary>View label scheme (47 labels for 3 components)</summary> |
|
|
|
| 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` | |
|
|
|
</details> |
|
|
|
### Accuracy |
|
|
|
| Type | Score | |
|
| --- | --- | |
|
| `TOKEN_ACC` | 99.69 | |
|
| `TAG_ACC` | 97.22 | |
|
| `POS_ACC` | 96.40 | |
|
| `MORPH_ACC` | 0.00 | |
|
| `DEP_UAS` | 91.81 | |
|
| `DEP_LAS` | 89.98 | |
|
| `ENTS_P` | 76.10 | |
|
| `ENTS_R` | 70.75 | |
|
| `ENTS_F` | 73.33 | |
|
| `SENTS_P` | 98.61 | |
|
| `SENTS_R` | 98.80 | |
|
| `SENTS_F` | 98.70 | |
