Update README.md
Browse files
README.md
CHANGED
@@ -25,7 +25,7 @@ oracle = pipeline('ner', model='dicta-il/dictabert-large-ner', aggregation_strat
|
|
25 |
from tokenizers.decoders import WordPiece
|
26 |
oracle.tokenizer.backend_tokenizer.decoder = WordPiece()
|
27 |
|
28 |
-
sentence = '
|
29 |
oracle(sentence)
|
30 |
```
|
31 |
|
@@ -34,24 +34,38 @@ Output:
|
|
34 |
[
|
35 |
{
|
36 |
"entity_group": "PER",
|
37 |
-
"score": 0.
|
38 |
-
"word": "
|
39 |
-
"start":
|
40 |
-
"end":
|
41 |
},
|
42 |
{
|
43 |
-
"entity_group": "
|
44 |
-
"score": 0.
|
45 |
-
"word": "
|
46 |
-
"start":
|
47 |
-
"end":
|
48 |
},
|
49 |
{
|
50 |
-
"entity_group": "
|
51 |
-
"score": 0.
|
52 |
-
"word": "
|
53 |
-
"start":
|
54 |
-
"end":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
}
|
56 |
]
|
57 |
```
|
|
|
25 |
from tokenizers.decoders import WordPiece
|
26 |
oracle.tokenizer.backend_tokenizer.decoder = WordPiece()
|
27 |
|
28 |
+
sentence = '''ืืื ืื-ืืืจืืื (16 ืืืืงืืืืจ 1886 - ื' ืืืกืื ืชืฉื"ื) ืืื ืืืื ืื ืืฉืจืืื ืืจืืฉ ืืืืฉืื ืืจืืฉืื ืฉื ืืืื ืช ืืฉืจืื.'''
|
29 |
oracle(sentence)
|
30 |
```
|
31 |
|
|
|
34 |
[
|
35 |
{
|
36 |
"entity_group": "PER",
|
37 |
+
"score": 0.9998988,
|
38 |
+
"word": "ืืื ืื - ืืืจืืื",
|
39 |
+
"start": 0,
|
40 |
+
"end": 13
|
41 |
},
|
42 |
{
|
43 |
+
"entity_group": "TIMEX",
|
44 |
+
"score": 0.99989706,
|
45 |
+
"word": "16 ืืืืงืืืืจ 1886",
|
46 |
+
"start": 15,
|
47 |
+
"end": 31
|
48 |
},
|
49 |
{
|
50 |
+
"entity_group": "TIMEX",
|
51 |
+
"score": 0.99991614,
|
52 |
+
"word": "ื' ืืืกืื ืชืฉื\"ื",
|
53 |
+
"start": 34,
|
54 |
+
"end": 48
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"entity_group": "TTL",
|
58 |
+
"score": 0.9931756,
|
59 |
+
"word": "ืืจืืฉ ืืืืฉืื",
|
60 |
+
"start": 68,
|
61 |
+
"end": 79
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"entity_group": "GPE",
|
65 |
+
"score": 0.9995702,
|
66 |
+
"word": "ืืฉืจืื",
|
67 |
+
"start": 96,
|
68 |
+
"end": 101
|
69 |
}
|
70 |
]
|
71 |
```
|