Update README.md
Browse files
README.md
CHANGED
|
@@ -3,18 +3,18 @@ license: mit
|
|
| 3 |
---
|
| 4 |
# Arabic NER
|
| 5 |
|
| 6 |
-
|
| 7 |
-
from transformers import pipeline, AutoModelForTokenClassification, AutoTokenizer
|
| 8 |
|
| 9 |
-
ner_model = AutoModelForTokenClassification.from_pretrained("ychen3411/arabic-ner-ace-gigabert")
|
| 10 |
-
ner_tokenizer = AutoTokenizer.from_pretrained("ychen3411/arabic-ner-ace-gigabert")
|
| 11 |
-
ner_pip = pipeline("ner", model=ner_model, tokenizer=ner_tokenizer, grouped_entities=True)
|
| 12 |
|
| 13 |
-
output = ner_pip('Protests break out across the US after Supreme Court overturns.')
|
| 14 |
-
print(output)
|
| 15 |
[{'entity_group': 'GPE', 'score': 0.9979881, 'word': 'us', 'start': 30, 'end': 32}, {'entity_group': 'ORG', 'score': 0.99898684, 'word': 'supreme court', 'start': 39, 'end': 52}]
|
| 16 |
|
| 17 |
-
output = ner_pip('قال وزير العدل التركي بكير بوزداغ إن أنقرة تريد 12 مشتبهاً بهم من فنلندا و 21 من السويد')
|
| 18 |
-
print(output)
|
| 19 |
[{'entity_group': 'PER', 'score': 0.9996214, 'word': 'وزير', 'start': 4, 'end': 8}, {'entity_group': 'ORG', 'score': 0.9952383, 'word': 'العدل', 'start': 9, 'end': 14}, {'entity_group': 'GPE', 'score': 0.9996675, 'word': 'التركي', 'start': 15, 'end': 21}, {'entity_group': 'PER', 'score': 0.9978992, 'word': 'بكير بوزداغ', 'start': 22, 'end': 33}, {'entity_group': 'GPE', 'score': 0.9997154, 'word': 'انقرة', 'start': 37, 'end': 42}, {'entity_group': 'PER', 'score': 0.9946885, 'word': 'مشتبها بهم', 'start': 51, 'end': 62}, {'entity_group': 'GPE', 'score': 0.99967396, 'word': 'فنلندا', 'start': 66, 'end': 72}, {'entity_group': 'PER', 'score': 0.99694425, 'word': '21', 'start': 75, 'end': 77}, {'entity_group': 'GPE', 'score': 0.99963355, 'word': 'السويد', 'start': 81, 'end': 87}]
|
| 20 |
-
|
|
|
|
| 3 |
---
|
| 4 |
# Arabic NER
|
| 5 |
|
| 6 |
+
```python
|
| 7 |
+
>>> from transformers import pipeline, AutoModelForTokenClassification, AutoTokenizer
|
| 8 |
|
| 9 |
+
>>> ner_model = AutoModelForTokenClassification.from_pretrained("ychen3411/arabic-ner-ace-gigabert")
|
| 10 |
+
>>> ner_tokenizer = AutoTokenizer.from_pretrained("ychen3411/arabic-ner-ace-gigabert")
|
| 11 |
+
>>> ner_pip = pipeline("ner", model=ner_model, tokenizer=ner_tokenizer, grouped_entities=True)
|
| 12 |
|
| 13 |
+
>>> output = ner_pip('Protests break out across the US after Supreme Court overturns.')
|
| 14 |
+
>>> print(output)
|
| 15 |
[{'entity_group': 'GPE', 'score': 0.9979881, 'word': 'us', 'start': 30, 'end': 32}, {'entity_group': 'ORG', 'score': 0.99898684, 'word': 'supreme court', 'start': 39, 'end': 52}]
|
| 16 |
|
| 17 |
+
>>> output = ner_pip('قال وزير العدل التركي بكير بوزداغ إن أنقرة تريد 12 مشتبهاً بهم من فنلندا و 21 من السويد')
|
| 18 |
+
>>> print(output)
|
| 19 |
[{'entity_group': 'PER', 'score': 0.9996214, 'word': 'وزير', 'start': 4, 'end': 8}, {'entity_group': 'ORG', 'score': 0.9952383, 'word': 'العدل', 'start': 9, 'end': 14}, {'entity_group': 'GPE', 'score': 0.9996675, 'word': 'التركي', 'start': 15, 'end': 21}, {'entity_group': 'PER', 'score': 0.9978992, 'word': 'بكير بوزداغ', 'start': 22, 'end': 33}, {'entity_group': 'GPE', 'score': 0.9997154, 'word': 'انقرة', 'start': 37, 'end': 42}, {'entity_group': 'PER', 'score': 0.9946885, 'word': 'مشتبها بهم', 'start': 51, 'end': 62}, {'entity_group': 'GPE', 'score': 0.99967396, 'word': 'فنلندا', 'start': 66, 'end': 72}, {'entity_group': 'PER', 'score': 0.99694425, 'word': '21', 'start': 75, 'end': 77}, {'entity_group': 'GPE', 'score': 0.99963355, 'word': 'السويد', 'start': 81, 'end': 87}]
|
| 20 |
+
```
|