add example image

.gitignore

@@ -0,0 +1 @@
+venv_unc*

app.py

@@ -210,6 +210,16 @@ demo = gr.Blocks()
 with demo:
     input_texts = gr.Variable([])
     gr.Markdown("**Detect Task Specification at Inference-time.**")
+    gr.Markdown("""Well-specified tasks should have a lower specification metric value. 
+                For example, with a close read, you can see that only Winogender schema sentence numbers (3) and (4) are well-specified:
+                the masked pronoun is coreferent with the `man` or `woman`, for the gendered pronoun resolution task, but the remainder are unspecfied.
+                             
+                In this example we have 100\% accurate detection with the specification metric near zero for only sentence (3) and (4).
+                <p align="center">
+                <img src="file/spec_metric_result.png" alt="results" width="500"/>
+                </p>
+                """)
+    
 
     gr.Markdown("**Follow the numbered steps below to test one of the pre-loaded options.** Once you get the hang of it, you can load a new model and/or provide your own input texts.")
     gr.Markdown(f"""1) Pick a preloaded BERT-like model.  
@@ -249,7 +259,7 @@ with demo:
         )
 
     with gr.Row():
-        get_text_btn = gr.Button("3) Click to load input texts.)")
+        get_text_btn = gr.Button("3) Click to load input texts.")
 
     get_text_btn.click(
         fn=display_input_texts,
@@ -262,7 +272,9 @@ with demo:
     with gr.Row():
         uncertain_btn = gr.Button("4) Click to get Task Specification Metric results!")
     gr.Markdown(
-        "If there is an * by a sentence number, then at least one top prediction for that sentence was non-gendered.")
+        """We expect a lower specification metric for well-specified tasks.
+        
+        Note: If there is an * by a sentence number, then at least one top prediction for that sentence was non-gendered.""")
 
     with gr.Row():
         female_fig = gr.Plot(type="auto")
@@ -270,7 +282,7 @@ with demo:
         female_df = gr.Dataframe()
     with gr.Row():
         display_text = gr.Textbox(
-            type="auto", label="Sample of text fed to model")
+            type="text", label="Sample of text fed to model")
 
     uncertain_btn.click(
         fn=predict_gender_pronouns,