debug

generic_ner.py

@@ -272,6 +272,49 @@ def conflicting_context(comp_entity, target_entity):
     return False  # No conflict
 
 
+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.
+    """
+    text_lower = text.lower()
+    partial_name_lower = partial_name.lower()
+
+    # 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
+
+    # If not found, return the original text (as a fallback)
+    return text.strip()
+
+
+def repair_names_in_entities(entities):
+    """
+    This function repairs the names in the entities by extracting the full name
+    from the text of the entity if a partial name (e.g., 'Washington') is incorrectly attached.
+    """
+    for entity in entities:
+        if "name" in entity and "pers" in entity["entity"]:
+            name = entity["name"].lower()
+            text = entity["text"].lower()
+
+            # Check if the attached name is part of the entity's text
+            if name in text:
+                # Extract the full name from the text by splitting around the attached name
+                full_name = extract_name_from_text(entity["text"], name)
+                entity["name"] = (
+                    full_name  # Replace the partial name with the full name
+                )
+
+    return entities
+
+
 def postprocess_entities(entities):
     # Step 1: Filter entities with the same text, keeping the one with the most dots in the 'entity' field
     entity_map = {}
@@ -294,6 +337,8 @@ 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(entities)
+
     return filtered_entities