Update

app.py

@@ -18,24 +18,14 @@ model_list = ['dumitrescustefan/bert-base-romanian-ner']
 st.sidebar.header("Select NER Model")
 model_checkpoint = st.sidebar.radio("", model_list)
 
-st.sidebar.write("For details of models: 'https://huggingface.co/dumitrescustefan/")
+st.sidebar.write("This demo is based on RoNER: 'https://github.com/dumitrescustefan/roner'")
 st.sidebar.write("")
 
-xlm_agg_strategy_info = "'aggregation_strategy' can be selected as 'simple' or 'none' for 'xlm-roberta' because of the RoBERTa model's tokenization approach."
-
-st.sidebar.header("Select Aggregation Strategy Type")
-if model_checkpoint == "akdeniz27/xlm-roberta-base-turkish-ner":
-    aggregation = st.sidebar.radio("", ('simple', 'none'))
-    st.sidebar.write(xlm_agg_strategy_info)
-elif model_checkpoint == "xlm-roberta-large-finetuned-conll03-english":
-    aggregation = st.sidebar.radio("", ('simple', 'none'))
-    st.sidebar.write(xlm_agg_strategy_info)
-    st.sidebar.write("")
-    st.sidebar.write("This English NER model is included just to show the zero-shot transfer learning capability of XLM-Roberta.")
-else:
-    aggregation = st.sidebar.radio("", ('first', 'simple', 'average', 'max', 'none'))
-    
-st.sidebar.write("Please refer 'https://huggingface.co/transformers/_modules/transformers/pipelines/token_classification.html' for entity grouping with aggregation_strategy parameter.")
+
+st.sidebar.header("Select type of PERSON detection")
+named_persons_only = st.sidebar.radio("", ('Proper nouns only', 'All nouns'))
+
+st.sidebar.write("Types of entities detected: 'PERSON', 'ORG', 'GPE', 'LOC', 'NAT_REL_POL', 'EVENT', 'LANGUAGE', 'WORK_OF_ART', 'DATETIME', 'PERIOD', 'MONEY', 'QUANTITY', 'NUMERIC', 'ORDINAL', 'FACILITY'")
 
 st.subheader("Select Text Input Method")
 input_method = st.radio("", ('Select from Examples', 'Write or Paste New Text'))
@@ -70,10 +60,9 @@ if Run_Button == True:
         if word["tag"]!="O":
             data.append({
                 "word": word["text"],
-                "tag": word["tag"],
+                "entity": word["tag"],
                 "start_char": word["start_char"],
-                "end_char": word["end_char"],
-                "span_after": word["span_after"],
+                "end_char": word["end_char"]
             })
     df = pd.DataFrame.from_dict(data)
     st.subheader("Recognized Entities")
@@ -87,15 +76,14 @@ if Run_Button == True:
     spacy_display["title"] = None
 
     for word in output["words"]:
-        #spacy_display["ents"].append({"start": entity["start"], "end": entity["end"], "label": entity["entity_group"]})
-        spacy_display["ents"].append({"start": word["start_char"], "end": word["end_char"], "label": word["tag"]})
+        if word["tag"]!="O":
+            spacy_display["ents"].append({"start": word["start_char"], "end": word["end_char"], "label": word["tag"]})
     
-    entity_list = ['O', 'PERSON', 'ORG', 'GPE', 'LOC', 'NAT_REL_POL',
+    entity_list = ['PERSON', 'ORG', 'GPE', 'LOC', 'NAT_REL_POL',
      'EVENT', 'LANGUAGE', 'WORK_OF_ART', 'DATETIME',
      'PERIOD', 'MONEY', 'QUANTITY', 'NUMERIC',
      'ORDINAL', 'FACILITY']
     colors = {
-        'O': '#FFF',
         'PERSON': '#F00',
         'ORG': '#F00',
         'GPE': '#F00',