Pepe

app.py

@@ -17,6 +17,13 @@ def display_text(example):
     # Sort entities by start
     entities = sorted(example["entities"], key=lambda x: x["start"])
 
+    for entity in entities:
+        entity_text = entity["text"]
+        # find in text
+        start = text.find(entity_text)
+        end = start + len(entity_text)
+        entity["start"] = start
+        entity["end"] = end
     # Chunk text
 
     if len(entities) == 0:
@@ -36,6 +43,9 @@ def display_text(example):
 
         last_index = end
 
+    if last_index < len(text):
+        chunks.append((text[last_index:], None))
+
     # description = entity["kg_result"]["detailedDescription"]["articleBody"]
     chunks = [(c, t) if t is not None else c for c, t in chunks]
     annotated_text(*chunks)
@@ -48,13 +58,10 @@ ds["train"] = ds["train"].select(elements)
 
 for ex in ds["train"]:
     st.write("=" * 80)
-    # display_text(ex)
-    st.write(ex["text"])
-
-    for ent in ex["entities"]:
-        entity_name = ent["text"]
-        entity_type = ent["type"]
-        entity_description = ent["kg_result"]["detailedDescription"]["articleBody"]
-        annotated_text(
-            (entity_name, "entity"), (f"({entity_type})", "type"), entity_description
-        )
+    display_text(ex)
+    with st.expander("Show entities"):
+        for ent in ex["entities"]:
+            entity_name = ent["text"]
+            entity_type = ent["type"]
+            entity_description = ent["kg_result"]["detailedDescription"]["articleBody"]
+            st.write(f"{entity_name} ({entity_type}): {entity_description}")