Update README.md
Browse files
README.md
CHANGED
|
@@ -26,6 +26,20 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 26 |
This model is a fine-tuned NER (named entity recognition) token classification model of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) (pre-trained cross-lingual ```RobertaModel```) on Wikipedia Japanese NER dataset by Stockmark Inc.<br>
|
| 27 |
See [here](https://github.com/stockmarkteam/ner-wikipedia-dataset) for the license of this dataset.
|
| 28 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
## Intended uses & limitations
|
| 30 |
|
| 31 |
```python
|
|
|
|
| 26 |
This model is a fine-tuned NER (named entity recognition) token classification model of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) (pre-trained cross-lingual ```RobertaModel```) on Wikipedia Japanese NER dataset by Stockmark Inc.<br>
|
| 27 |
See [here](https://github.com/stockmarkteam/ner-wikipedia-dataset) for the license of this dataset.
|
| 28 |
|
| 29 |
+
Each token is labeled by :
|
| 30 |
+
|
| 31 |
+
| Label id | Tag | Description |
|
| 32 |
+
|---|---|---|
|
| 33 |
+
| 0 | O | others or nothing |
|
| 34 |
+
| 1 | PER | person |
|
| 35 |
+
| 2 | ORG | general corporation organization |
|
| 36 |
+
| 3 | ORG-P | political organization |
|
| 37 |
+
| 4 | ORG-O | other organization |
|
| 38 |
+
| 5 | LOC | location |
|
| 39 |
+
| 6 | INS | institution, facility |
|
| 40 |
+
| 7 | PRD | product |
|
| 41 |
+
| 8 | EVT | event |
|
| 42 |
+
|
| 43 |
## Intended uses & limitations
|
| 44 |
|
| 45 |
```python
|