add comp back

generic_ner.py

@@ -263,7 +263,7 @@ def conflicting_context(comp_entity, target_entity):
 def extract_name_from_text(text, partial_name):
     """
     Extracts the full name from the entity's text based on the partial name.
-    This function assumes that the partial name is contained within the full name in the text.
+    This function assumes that the partial name is part of a full name, which starts with capitalized letters.
     """
     text_lower = text.lower()
     partial_name_lower = partial_name.lower()
@@ -271,12 +271,31 @@ def extract_name_from_text(text, partial_name):
     # Find the position of the partial name in the text
     name_start_idx = text_lower.find(partial_name_lower)
 
-    # Assuming the full name is everything before or after the partial name
-    # Here, we assume the name is likely at the beginning of the sentence
     if name_start_idx != -1:
-        # Extract the part of the text containing the full name
-        full_name = text[: name_start_idx + len(partial_name)]
-        return full_name.strip()  # Return the full name, trimming any spaces
+        # Split the text into words
+        words = text.split()
+
+        # Find the position of the partial name in the word list
+        for i, word in enumerate(words):
+            if partial_name_lower in word.lower():
+                # Initialize full name with the partial name
+                full_name = [word]
+
+                # Check previous words to see if they start with a capital letter
+                j = i - 1
+                while j >= 0 and words[j][0].isupper():
+                    full_name.insert(0, words[j])
+                    j -= 1
+
+                # Check next words to see if they start with a capital letter
+                k = i + 1
+                while k < len(words) and words[k][0].isupper():
+                    full_name.append(words[k])
+                    k += 1
+
+                return " ".join(
+                    full_name
+                ).strip()  # Join the words to form the full name
 
     # If not found, return the original text (as a fallback)
     return text.strip()
@@ -350,7 +369,7 @@ def postprocess_entities(entities):
     # Step 2: Attach "comp.function" entities to the closest other entities
     filtered_entities = attach_comp_to_closest(filtered_entities)
 
-    # filtered_entities = repair_names_in_entities(filtered_entities)
+    filtered_entities = repair_names_in_entities(filtered_entities)
 
     # Step 3: Remove entities that are not useful for NEL
     # filtered_entities = clean_coarse_entities(filtered_entities)