Update app.py

app.py

@@ -3,7 +3,10 @@ import pandas as pd
 import transformers
 from transformers import  pipeline, TokenClassificationPipeline, BertForTokenClassification , AutoTokenizer , TextClassificationPipeline , AutoModelForSequenceClassification
 
-x = st.text_area('enter')
+st.header("Knowledge extraction on Endocrine disruptors")
+st.text("This tool lets you extract relation triples concerning interactions between: endocrine disrupting chemicals, hormones, receptors and cancers.")
+st.text("It is the result of an end of studies project within ESI school and dedicated to biomedical researchers looking to extract precise information about the subject without digging into long publications.")
+x = st.text_area('Entre you text on EDCs:')
 
 #model.to("cpu")
 tokenizer = AutoTokenizer.from_pretrained("dmis-lab/biobert-large-cased-v1.1", truncation = True, padding=True, model_max_length=512,)
@@ -13,6 +16,7 @@ model_checkpoint = BertForTokenClassification.from_pretrained("dexay/Ner2HgF", )
 model_re = AutoModelForSequenceClassification.from_pretrained("dexay/reDs3others", )
 token_classifier = pipeline("token-classification", tokenizer = tokenizer,model=model_checkpoint,  )
 
+st.text("Knowledge extraction is in progress ...")
 
 biotext = x
 
@@ -144,6 +148,9 @@ for itsent in az:
 
 #lstSentEnc,lstSentEnt,lstSentbilbl
 
+st.text("Entities detected, Next: Relation detection ...")
+
+
 # Relation extraction part
 
 token_classifier = pipeline("text-classification", tokenizer = tokenizer,model=model_re, 
@@ -203,7 +210,7 @@ edccan = []
 
 
 for i in range(len(outrelbl)):
-  if outrelbl[i]== "other":
+  if outrelbl[i] != "other":
     edccan += [[lstSentEnc[i],lstSentEnt[i][0], lstSentEnt[i][1],lstSentbilbl[i][0]+" "+outrelbl[i][:-7]+" "+lstSentbilbl[i][1]]]
  
 edccandf = pd.DataFrame(edccan, columns= ["Sentence", "Entity 1", "Entity 2", "Relation"] )