Update README.md
Browse files
README.md
CHANGED
@@ -41,6 +41,7 @@ The model has been first fine-tuned on WikiNER, then focused on the Italian lang
|
|
41 |
|
42 |
```python
|
43 |
from transformers import AutoModelForTokenClassification, AutoTokenizer
|
|
|
44 |
import re
|
45 |
import string
|
46 |
|
@@ -51,26 +52,27 @@ text = "mi chiamo marco rossi, vivo a roma e lavoro per l'agenzia spaziale itali
|
|
51 |
|
52 |
for p in string.punctuation:
|
53 |
text = text.replace(p, " " + p + " ")
|
54 |
-
|
55 |
-
ner(
|
|
|
56 |
|
57 |
[{'entity_group': 'PER',
|
58 |
-
'score': 0.
|
59 |
'word': 'marco rossi',
|
60 |
'start': 9,
|
61 |
'end': 21},
|
62 |
{'entity_group': 'LOC',
|
63 |
-
'score': 0.
|
64 |
'word': 'roma',
|
65 |
'start': 31,
|
66 |
'end': 36},
|
67 |
{'entity_group': 'ORG',
|
68 |
-
'score': 0.
|
69 |
'word': 'agenzia spaziale italiana',
|
70 |
'start': 53,
|
71 |
'end': 79},
|
72 |
{'entity_group': 'MISC',
|
73 |
-
'score': 0.
|
74 |
'word': 'missione prisma',
|
75 |
'start': 85,
|
76 |
'end': 101}]
|
|
|
41 |
|
42 |
```python
|
43 |
from transformers import AutoModelForTokenClassification, AutoTokenizer
|
44 |
+
from transformers import pipeline
|
45 |
import re
|
46 |
import string
|
47 |
|
|
|
52 |
|
53 |
for p in string.punctuation:
|
54 |
text = text.replace(p, " " + p + " ")
|
55 |
+
|
56 |
+
ner = pipeline("ner", model=model, tokenizer=tokenizer)
|
57 |
+
ner(text, aggregation_strategy="simple")
|
58 |
|
59 |
[{'entity_group': 'PER',
|
60 |
+
'score': 0.9929623,
|
61 |
'word': 'marco rossi',
|
62 |
'start': 9,
|
63 |
'end': 21},
|
64 |
{'entity_group': 'LOC',
|
65 |
+
'score': 0.9898509,
|
66 |
'word': 'roma',
|
67 |
'start': 31,
|
68 |
'end': 36},
|
69 |
{'entity_group': 'ORG',
|
70 |
+
'score': 0.9905911,
|
71 |
'word': 'agenzia spaziale italiana',
|
72 |
'start': 53,
|
73 |
'end': 79},
|
74 |
{'entity_group': 'MISC',
|
75 |
+
'score': 0.92474234,
|
76 |
'word': 'missione prisma',
|
77 |
'start': 85,
|
78 |
'end': 101}]
|