|
--- |
|
language: |
|
- zh |
|
|
|
license: apache-2.0 |
|
|
|
tags: |
|
- Roberta |
|
- CWS |
|
- Chinese Word Segmentation |
|
- Chinese |
|
|
|
inference: false |
|
--- |
|
#### How to use |
|
|
|
You can use this model with Transformers *pipeline* for token-classification. |
|
|
|
```python |
|
from transformers import AutoTokenizer, AutoModelForTokenClassification |
|
from transformers import pipeline |
|
|
|
nlp = pipeline("token-classification", model="enpchina/cws_chinese_roberta_shunpao", aggregation_strategy="simple") |
|
example = "非兩君之盡心於民事，以實心而行實政， 其能得此，於諸紳士也哉。" |
|
cws_results = nlp(example) |
|
print(cws_results) |
|
print() |
|
tab = [w["word"].replace(" ","") for w in cws_results] |
|
print(tab) |
|
print() |
|
print(" ".join(tab)) |
|
``` |
|
|
