better postprocessing

app.py

@@ -39,21 +39,29 @@ def postprocess(classifications):
                     j += 1
                 entities.append((ner_map[classifications[i]['entity']].split('-')[1], classifications[i]['start'],
                                  classifications[j - 1]['end']))
-    to_remove = []
-    merged_entities = []
-    for i in range(len(entities)):
-        for j in range(i + 1, len(entities)):
-            if entities[i] != entities[j] and entities[i][0] == entities[j][0] and (entities[i][2] == entities[j][1] or
-                                                                                    entities[i][1] == entities[j][2]):
-                to_remove.append(entities[i])
-                to_remove.append(entities[j])
+    while True:
+        merged = False
+        to_remove = []
+        merged_entities = []
+        for i in range(len(entities)):
+            for j in range(i + 1, len(entities)):
+                if entities[i] != entities[j] and entities[i][0] == entities[j][0] and \
+                        (entities[i][2] == entities[j][1] or entities[i][1] == entities[j][2]):
+                    to_remove.append(entities[i])
+                    to_remove.append(entities[j])
 
-                new_start = min(entities[i][1], entities[j][1])
-                new_end = max(entities[i][2], entities[j][2])
-                merged_entities.append((entities[i][0], new_start, new_end))
-    for ent in to_remove:
-        entities.remove(ent)
-    entities += merged_entities
+                    new_start = min(entities[i][1], entities[j][1])
+                    new_end = max(entities[i][2], entities[j][2])
+                    merged_entities.append((entities[i][0], new_start, new_end))
+                    merged = True
+                    break
+            if merged:
+                break
+        for ent in to_remove:
+            entities.remove(ent)
+        entities += merged_entities
+        if not merged:
+            break
     return entities
 
 
@@ -80,9 +88,13 @@ intf = gr.Interface(fn=apply_ner, inputs="text", outputs="html", title='Slovak N
                                "štyroch prípadov variantu omikron na Slovensku."],
                               ["Čaputová opakovane tvrdí, že \"spravodlivosť na Slovensku neplatí vždy pre všetkých "
                                "rovnako\"."],
+                              ["Informácie o týchto veľkolepých plánoch prišli týždeň po tom, ako sa japonský "
+                               "miliardár Jusaku Maezawa vrátil z 12-dňového pobytu na Medzinárodnej vesmírnej stanici "
+                               "(ISS), čím sa stal prvým vesmírnym turistom, ktorý cestoval na ISS za viac ako desať "
+                               "rokov."],
                               ["Minister financií a líder mandátovo najsilnejšieho hnutia OĽaNO Igor Matovič "
                                "upozorňuje, že následky tretej vlny budú na Slovensku veľmi veľké."],
-                              ["Začiatkom roka sa objavili nezhody medzi Richardom Sulíkom a šéfom hnutia OĽANO "
+                              ["Začiatkom roka 2021 sa objavili nezhody medzi Richardom Sulíkom a šéfom hnutia OĽANO "
                                "Igorom Matovičom, ktoré v istej miere pretrvávajú aj dodnes."]],
                     description="Named-entity recognition (NER) labels named-entities in unstructured text. This "
                                 "implementation supports three labels: person (OSOBA), organization (ORGANIZÁCIA) and "