Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -7,35 +7,14 @@ from extractive_summarization import summarize_with_textrank, summarize_with_lsa
|
|
7 |
from abstractive_summarization import summarize_with_bart_cnn, summarize_with_bart_ft, summarize_with_led, summarize_with_t5
|
8 |
from keyword_extraction import extract_keywords
|
9 |
from keyphrase_extraction import extract_sentences_with_obligations
|
10 |
-
from transformers import AutoModelForTokenClassification, AutoTokenizer
|
11 |
-
import torch
|
12 |
#from blanc import BlancHelp
|
13 |
|
14 |
-
|
15 |
# Load in ToS
|
16 |
dataset = load_dataset("EE21/ToS-Summaries")
|
17 |
|
18 |
|
19 |
-
model_name = "dbmdz/bert-large-cased-finetuned-conll03-english"
|
20 |
-
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
21 |
-
model = AutoModelForTokenClassification.from_pretrained(model_name)
|
22 |
-
|
23 |
-
def extract_organization_names(text):
|
24 |
-
inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
|
25 |
-
outputs = model(**inputs)
|
26 |
-
|
27 |
-
predictions = torch.argmax(outputs.logits, dim=2)
|
28 |
-
entities = [tokenizer.convert_ids_to_tokens(inputs.input_ids[0][idx]) for idx, pred in enumerate(predictions[0]) if model.config.id2label[pred.item()] == 'B-ORG']
|
29 |
-
return " ".join(entities)
|
30 |
-
|
31 |
-
# Apply this function to your dataset
|
32 |
-
tos_titles = [extract_organization_names(doc['plain_text']) for doc in dataset['train']]
|
33 |
-
|
34 |
-
|
35 |
# Extract titles or identifiers for the ToS
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
|
40 |
|
41 |
# Set page to wide mode
|
|
|
7 |
from abstractive_summarization import summarize_with_bart_cnn, summarize_with_bart_ft, summarize_with_led, summarize_with_t5
|
8 |
from keyword_extraction import extract_keywords
|
9 |
from keyphrase_extraction import extract_sentences_with_obligations
|
|
|
|
|
10 |
#from blanc import BlancHelp
|
11 |
|
|
|
12 |
# Load in ToS
|
13 |
dataset = load_dataset("EE21/ToS-Summaries")
|
14 |
|
15 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
# Extract titles or identifiers for the ToS
|
17 |
+
tos_titles = [f"Document {i}" for i in range(len(dataset['train']))]
|
|
|
|
|
18 |
|
19 |
|
20 |
# Set page to wide mode
|