Update cross_encoder_reranking_train.py

cross_encoder_reranking_train.py

@@ -145,19 +145,19 @@ def extract_text(content_dict, text_type="full"):
         filtered_dict = process_single_patent(content_dict)
         all_text = []
         # Start with abstract for better context at the beginning
-        if "pa01" in content_dict:
-            all_text.append(content_dict["pa01"])
+        # if "pa01" in content_dict:
+        #     all_text.append(content_dict["pa01"])
 
         # For claims, paragraphs and features, we take only the top-10 most relevant
         # Add claims
         for claim in filtered_dict["claims"][:10]:
             all_text.append(claim)
-        # Add paragraphs
-        for paragraph in filtered_dict["paragraphs"][:10]:
-            all_text.append(paragraph)
         # Add features
         for feature in filtered_dict["features"][:10]:
             all_text.append(feature)
+        # Add paragraphs
+        for paragraph in filtered_dict["paragraphs"][:10]:
+            all_text.append(paragraph)
         
         return " ".join(all_text)