Update app.py

app.py

@@ -7,35 +7,14 @@ from extractive_summarization import summarize_with_textrank, summarize_with_lsa
 from abstractive_summarization import summarize_with_bart_cnn, summarize_with_bart_ft, summarize_with_led, summarize_with_t5
 from keyword_extraction import extract_keywords
 from keyphrase_extraction import extract_sentences_with_obligations
-from transformers import AutoModelForTokenClassification, AutoTokenizer
-import torch
 #from blanc import BlancHelp
 
-
 # Load in ToS
 dataset = load_dataset("EE21/ToS-Summaries")
 
 
-model_name = "dbmdz/bert-large-cased-finetuned-conll03-english"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForTokenClassification.from_pretrained(model_name)
-
-def extract_organization_names(text):
-    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
-    outputs = model(**inputs)
-
-    predictions = torch.argmax(outputs.logits, dim=2)
-    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']
-    return " ".join(entities)
-
-# Apply this function to your dataset
-tos_titles = [extract_organization_names(doc['plain_text']) for doc in dataset['train']]
-
-
 # Extract titles or identifiers for the ToS
-#tos_titles = [f"Document {i}" for i in range(len(dataset['train']))]
-
-
+tos_titles = [f"Document {i}" for i in range(len(dataset['train']))]
 
         
 # Set page to wide mode