Update cross_encoder_reranking_train.py

cross_encoder_reranking_train.py

@@ -129,8 +129,8 @@ def extract_text(content_dict, text_type="full"):
         # Extract everything
         all_text = []
         # Start with title and abstract for better context at the beginning
-        if "title" in content_dict:
-            all_text.append(content_dict["title"])
+        # if "title" in content_dict:
+        #     all_text.append(content_dict["title"]) do with this on next
         if "pa01" in content_dict:
             all_text.append(content_dict["pa01"])
             
@@ -145,8 +145,10 @@ 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 "title" in content_dict:
+            all_text.append(content_dict["title"])
+        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