Model and Interface Update

app.py

@@ -19,28 +19,49 @@ st.title("Demo for Turkish NER Models")
 st.write("For details of models: 'https://huggingface.co/akdeniz27/")
 st.write("Please refer 'https://huggingface.co/transformers/_modules/transformers/pipelines/token_classification.html' for entity grouping with aggregation_strategy parameter.")
 
+model_list = ['akdeniz27/bert-base-turkish-cased-ner',
+             'akdeniz27/convbert-base-turkish-cased-ner',
+             'akdeniz27/xlm-roberta-base-turkish-ner',
+             'xlm-roberta-large-finetuned-conll03-english']
+
 st.sidebar.header("Select NER Model")
-selection = st.sidebar.radio("", ('bert-base-turkish-cased-ner', 'convbert-base-turkish-cased-ner', 'xlm-roberta-base-turkish-ner'))
-if selection == "bert-base-turkish-cased-ner":
-    model_checkpoint = "akdeniz27/bert-base-turkish-cased-ner"    
-elif selection == "convbert-base-turkish-cased-ner":
-    model_checkpoint = "akdeniz27/convbert-base-turkish-cased-ner"
-elif selection == "xlm-roberta-base-turkish-ner":
-    model_checkpoint = "akdeniz27/xlm-roberta-base-turkish-ner"
+model_checkpoint = st.sidebar.radio("", model_list)
+# if selection == "bert-base-turkish-cased-ner":
+#     model_checkpoint = "akdeniz27/bert-base-turkish-cased-ner"    
+# elif selection == "convbert-base-turkish-cased-ner":
+#     model_checkpoint = "akdeniz27/convbert-base-turkish-cased-ner"
+# elif selection == "xlm-roberta-base-turkish-ner":
+#     model_checkpoint = "akdeniz27/xlm-roberta-base-turkish-ner"
+# elif selection == "xlm-roberta-large-finetuned-conll03-english":
+#     model_checkpoint = "xlm-roberta-large-finetuned-conll03-english"
+
+st.sidebar.write("")
+st.sidebar.write("")
+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")
-aggregation = st.sidebar.radio("", ('first', 'simple', 'average', 'max', 'none'))
+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.header("Select Text Input Method")
+st.subheader("Select Text Input Method")
 input_method = st.radio("", ('Select among Examples', 'Write or Paste New Text'))
 if input_method == 'Select among Examples':
-    st.header("Select Text")
-    selected_text = st.selectbox('', example_list, index=0, key=1)
-    st.header("Selected Text")
-    input_text = st.text_area("", selected_text, height=128, max_chars=None, key=2)
+    selected_text = st.selectbox('Select Text from List', example_list, index=0, key=1)
+    st.subheader("Text to Run")
+    input_text = st.text_area("Selected Text", selected_text, height=128, max_chars=None, key=2)
 elif input_method == "Write or Paste New Text":
-    st.header("Write or Paste New Text")
-    input_text = st.text_area('', value="", height=128, max_chars=None, key=2)
+    st.subheader("Text to Run")
+    input_text = st.text_area('Write or Paste Text Below', value="", height=128, max_chars=None, key=2)
 
 def setModel(model_checkpoint, aggregation):
     model = AutoModelForTokenClassification.from_pretrained(model_checkpoint)