Update app.py

app.py

@@ -51,7 +51,7 @@ def get_all_predictions(text_sentence, top_clean=5):
     predict = bert_model(input_ids)[0]
   bert = decode(bert_tokenizer, predict[0, mask_idx, :].topk(top_k*5).indices.tolist(), top_clean)
   cls = decode(bert_tokenizer, predict[0, 0, :].topk(top_k*5).indices.tolist(), top_clean)
-  return {'sentence':text_sentence,'Masked position': bert,'[CLS]':cls}
+  return {'Input sentence':text_sentence,'Masked position': bert,'[CLS]':cls}
 
 def get_bert_prediction(input_text,top_k):
   try:
@@ -83,9 +83,9 @@ st.markdown("""
         <small style="font-size:18px; color: #8f8f8f">This app is used to qualitatively examine the performance of pretrained models to do NER , <a href="https://ajitrajasekharan.github.io/2021/01/02/my-first-post.html"><b>with no fine tuning</b></small></a>
         """, unsafe_allow_html=True)
   #st.write("https://ajitrajasekharan.github.io/2021/01/02/my-first-post.html")
-st.write("The neighborhood of CLS vectors as well as the model prediction for a blank position are examined")
-st.write("To examine model prediction for a position, enter the token [MASK] or <mask>")
-st.write("To examine just the [CLS] vector, enter a word/phrase or sentence. Example: eGFR or EGFR or non small cell lung cancer")
+st.write("Model prediction for a masked  position as well as the neighborhood of CLS vector for input text can be examined")
+st.write("   - To examine model prediction for a position, enter the token [MASK] or <mask>")
+st.write("   - To examine just the [CLS] vector, enter a word/phrase or sentence. Example: eGFR or EGFR or non small cell lung cancer")
 top_k = st.sidebar.slider("Select how many predictions do you need", 1 , 50, 20) #some times it is possible to have less words
 print(top_k)