Update app.py

app.py

@@ -29,10 +29,10 @@ def sentiment_analysis(sentence, model_name):
         "negative": negative,
     }
     type_dic = {
-        "CCCC/ARCH_Tuned_RoBERTa":"roberta",
-        "CCCC/FNCH_Tuned_RoBERTa":"roberta",
-        "CCCC/AREN_Tuned_RoBERTa":"roberta",
-        "CCCC/FNEN_Tuned_RoBERTa":"roberta",
+        "CCCC/RoBERTa_Chinese_AnnualReport_tuned":"roberta",
+        "CCCC/RoBERTa_Chinese_Financial_News_tuned":"roberta",
+        "CCCC/RoBERTa_English_AnnualReport_tuned":"roberta",
+        "CCCC/RoBERTa_English_Financial_News_tuned":"roberta",
     }
     testdata = []
     for i,sentence in enumerate(sentences):
@@ -73,11 +73,11 @@ def sentiment_analysis(sentence, model_name):
 
 demo = gr.Interface(fn=sentiment_analysis,
                     inputs = [gr.Textbox(placeholder="Enter sentence here. If you have multiple sentences, separate them with '\\n'.",label="Sentence",lines=5),
-                            gr.Radio(choices=["ARCH_Tuned_RoBERTa","FNCH_Tuned_RoBERTa","AREN_Tuned_RoBERTa",
-                                              "FNEN_Tuned_RoBERTa"], label="Model Selection")],
+                            gr.Radio(choices=["RoBERTa_Chinese_AnnualReport_tuned","RoBERTa_Chinese_Financial_News_tuned","RoBERTa_English_AnnualReport_tuned",
+                                              "RoBERTa_English_Financial_News_tuned"], label="Model Selection")],
                     outputs=gr.Textbox(label="Sentiment",lines=5),
                     # css = "label.svelte-1p9xokt{width:35%;}",
-                    title = "Sentiment Analysis Based on Prompt-tuned PLM"
+                    title = "Prompt Learning-Based Disclosure Sentiment Detection"
         )
     
 demo.launch()