Update README.md
Browse files
README.md
CHANGED
@@ -22,7 +22,7 @@ oracle = pipeline('ner', model='dicta-il/dictabert-ner', aggregation_strategy='s
|
|
22 |
from tokenizers.decoders import WordPiece
|
23 |
oracle.tokenizer.backend_tokenizer.decoder = WordPiece()
|
24 |
|
25 |
-
sentence = '
|
26 |
oracle(sentence)
|
27 |
```
|
28 |
|
@@ -31,24 +31,38 @@ Output:
|
|
31 |
[
|
32 |
{
|
33 |
"entity_group": "PER",
|
34 |
-
"score": 0.
|
35 |
-
"word": "
|
36 |
-
"start":
|
37 |
-
"end":
|
38 |
},
|
39 |
{
|
40 |
-
"entity_group": "
|
41 |
-
"score": 0.
|
42 |
-
"word": "
|
43 |
-
"start":
|
44 |
-
"end":
|
45 |
},
|
46 |
{
|
47 |
-
"entity_group": "
|
48 |
-
"score": 0.
|
49 |
-
"word": "
|
50 |
-
"start":
|
51 |
-
"end":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
}
|
53 |
]
|
54 |
```
|
|
|
22 |
from tokenizers.decoders import WordPiece
|
23 |
oracle.tokenizer.backend_tokenizer.decoder = WordPiece()
|
24 |
|
25 |
+
sentence = '''ืืื ืื-ืืืจืืื (16 ืืืืงืืืืจ 1886 - ื' ืืืกืื ืชืฉื"ื) ืืื ืืืื ืื ืืฉืจืืื ืืจืืฉ ืืืืฉืื ืืจืืฉืื ืฉื ืืืื ืช ืืฉืจืื.'''
|
26 |
oracle(sentence)
|
27 |
```
|
28 |
|
|
|
31 |
[
|
32 |
{
|
33 |
"entity_group": "PER",
|
34 |
+
"score": 0.9999443,
|
35 |
+
"word": "ืืื ืื - ืืืจืืื",
|
36 |
+
"start": 0,
|
37 |
+
"end": 13
|
38 |
},
|
39 |
{
|
40 |
+
"entity_group": "TIMEX",
|
41 |
+
"score": 0.99987966,
|
42 |
+
"word": "16 ืืืืงืืืืจ 1886",
|
43 |
+
"start": 15,
|
44 |
+
"end": 31
|
45 |
},
|
46 |
{
|
47 |
+
"entity_group": "TIMEX",
|
48 |
+
"score": 0.9998579,
|
49 |
+
"word": "ื' ืืืกืื ืชืฉื\"ื",
|
50 |
+
"start": 34,
|
51 |
+
"end": 48
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"entity_group": "TTL",
|
55 |
+
"score": 0.99963045,
|
56 |
+
"word": "ืืจืืฉ ืืืืฉืื",
|
57 |
+
"start": 68,
|
58 |
+
"end": 79
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"entity_group": "GPE",
|
62 |
+
"score": 0.9997943,
|
63 |
+
"word": "ืืฉืจืื",
|
64 |
+
"start": 96,
|
65 |
+
"end": 101
|
66 |
}
|
67 |
]
|
68 |
```
|