Update README.md
Browse files
README.md
CHANGED
|
@@ -78,33 +78,6 @@ The pre-trained model can recognize the following entities:
|
|
| 78 |
|
| 79 |
[Find here a complete example to use this model](https://github.com/hatmimoha/arabic-ner)
|
| 80 |
|
| 81 |
-
Here is the map from index to label:
|
| 82 |
-
|
| 83 |
-
```
|
| 84 |
-
id2label = {
|
| 85 |
-
"0": "B-PERSON",
|
| 86 |
-
"1": "I-PERSON",
|
| 87 |
-
"2": "B-ORGANIZATION",
|
| 88 |
-
"3": "I-ORGANIZATION",
|
| 89 |
-
"4": "B-LOCATION",
|
| 90 |
-
"5": "I-LOCATION",
|
| 91 |
-
"6": "B-DATE",
|
| 92 |
-
"7": "I-DATE"",
|
| 93 |
-
"8": "B-COMPETITION",
|
| 94 |
-
"9": "I-COMPETITION",
|
| 95 |
-
"10": "B-PRIZE",
|
| 96 |
-
"11": "I-PRIZE",
|
| 97 |
-
"12": "O",
|
| 98 |
-
"13": "B-PRODUCT",
|
| 99 |
-
"14": "I-PRODUCT",
|
| 100 |
-
"15": "B-EVENT",
|
| 101 |
-
"16": "I-EVENT",
|
| 102 |
-
"17": "B-DISEASE",
|
| 103 |
-
"18": "I-DISEASE",
|
| 104 |
-
}
|
| 105 |
-
|
| 106 |
-
```
|
| 107 |
-
|
| 108 |
## Training Corpus
|
| 109 |
|
| 110 |
The training corpus is made of 378.000 tokens (14.000 sentences) collected from the Web and annotated manually.
|
|
|
|
| 78 |
|
| 79 |
[Find here a complete example to use this model](https://github.com/hatmimoha/arabic-ner)
|
| 80 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
## Training Corpus
|
| 82 |
|
| 83 |
The training corpus is made of 378.000 tokens (14.000 sentences) collected from the Web and annotated manually.
|