added more details page. modified the explore more section design.

app.py

@@ -113,8 +113,8 @@ def get_similar_paper(
     
     # set up elements to show 
     out = [
-        gr.update(choices=display_title, interactive=True, visible=False), # set of papers (radio)
-        gr.update(choices=input_sentences, interactive=True, visible=False) # submission sentences 
+        gr.update(choices=display_title, interactive=True), # set of papers (radio)
+        gr.update(choices=input_sentences, interactive=True) # submission sentences 
     ]
     
     # set up elements to visualize upfront
@@ -178,6 +178,12 @@ def get_similar_paper(
     # progress status
     out += [gr.update(value='Done (in %0.1f seconds)'%(retrieval_time+highlight_time), visible=True)]
     
+    # result 2 description
+    desc = """
+        ##### Click a paper by %s on the left (sorted by affinity scores), and a sentence from the submission on the right, to see which parts the paper are relevant.
+    """%results['name']
+    out += [gr.update(value=desc)]
+    
     # add the search results to pass on to the Gradio State varaible
     out += [results]
     
@@ -186,13 +192,12 @@ def get_similar_paper(
 def show_more(info):
     # show the interactive part of the app
     return (
-        gr.update(value="""
-            ### Click on different papers by %s below (sorted by their affinity scores) to see other relevant parts!
-            """%info['name'], visible=True), # description
+        gr.update(visible=True), # description
         gr.update(visible=True), # set of papers
         gr.update(visible=True), # submission sentences
         gr.update(visible=True), # title row
-        gr.update(visible=True), # abstract row
+        gr.update(visible=True), # affinity row
+        gr.update(visible=True), # highlight legend
     )
 
 def show_status():
@@ -223,8 +228,8 @@ def change_paper(selected_papers_radio, info={}):
         aff_score = info[selected_papers_radio]['doc_score']
         highlights = info[selected_papers_radio]['highlight']
         url = info[selected_papers_radio]['url']
-        title_out = """<a href="%s" target="_blank"><h4>%s</h4></a>"""%(url, title)
-        aff_score_out = '#### Affinity Score: %s'%aff_score
+        title_out = """<a href="%s" target="_blank"><h5>%s</h5></a>"""%(url, title)
+        aff_score_out = '##### Affinity Score: %s'%aff_score
         return title_out, abstract, aff_score_out, highlights['0']
 
     else:
@@ -235,24 +240,26 @@ with gr.Blocks(css='style.css') as demo:
     
     # Text description about the app and disclaimer
     ### TEXT Description
-    # TODO add instruction video link
-    gr.Markdown(
-        """
-# R2P2: Matching Reviewers to Papers in Peer Review
 
-#### Who is R2P2 for?
+    # General instruction
+    general_instruction = """
+# R2P2: Reviewer TO Paper in Peer review
+
+#### Who is it for?
 It is for meta-reviewers, area chairs, program chairs, or anyone who oversees the submission-reviewer matching process in peer review for acadmeic conferences, journals, and grants. 
 
 #### How does it help?
-A typical meta-reviewer workflow lacks supportive information on what makes the pre-selected candidate reviewers good fit for the submission. Only the **affinity scores** between the reviewer and the paper are provided, with no additional detail. 
+A typical meta-reviewer workflow lacks supportive information on **what makes the pre-selected candidate reviewers a good fit** for the submission. Only affinity scores between the reviewer and the paper are shown, without additional detail. 
 
-R2P2 provide more information about each reviewer. It searches for the most relevant papers among the reviewer's previous publications and highlights relevant parts within them. 
-
-Check out [this video]() for a quick demo of what R2P2 is, and how it can help!
+R2P2 provides more information about each reviewer. It searches for the most relevant papers among the reviewer's previous publications and highlights relevant parts within them. 
+    """
+    # TODO add instruction video link
+    # More details (video, addendum)
+    more_details_instruction = """Check out <a href="", target="_blank">this video</a> for a quick demo of what R2P2 is and how it can help. For more details (e.g., relevant work, privacy policy, disclaimer), refer to <a href="file/details.html", target="_blank">here</a>."""
 
--------
-        """
-    ) 
+    gr.Markdown(general_instruction)
+    gr.HTML(more_details_instruction)
+    gr.Markdown("""---""")
     
     ### INPUT
     with gr.Row() as input_row:
@@ -289,7 +296,7 @@ Check out [this video]() for a quick demo of what R2P2 is, and how it can help!
             sent_pair_source1_1 = gr.Textbox(label='Sentence from Submission', visible=False)
             sent_pair_source1_1_hl = gr.components.Interpretation(sent_pair_source1_1)
         with gr.Column(scale=4):
-            sent_pair_candidate1_1 = gr.Textbox(label='Sentence from Paper', visible=False)
+            sent_pair_candidate1_1 = gr.Textbox(label="Sentence from Reviewer's Paper", visible=False)
             sent_pair_candidate1_1_hl = gr.components.Interpretation(sent_pair_candidate1_1)
     with gr.Row() as rel1_2:
         with gr.Column(scale=1):
@@ -298,7 +305,7 @@ Check out [this video]() for a quick demo of what R2P2 is, and how it can help!
             sent_pair_source1_2 = gr.Textbox(label='Sentence from Submission', visible=False)
             sent_pair_source1_2_hl = gr.components.Interpretation(sent_pair_source1_2)
         with gr.Column(scale=4):
-            sent_pair_candidate1_2 = gr.Textbox(label='Sentence from Paper', visible=False)
+            sent_pair_candidate1_2 = gr.Textbox(label="Sentence from Reviewer's Paper", visible=False)
             sent_pair_candidate1_2_hl = gr.components.Interpretation(sent_pair_candidate1_2)
     
     with gr.Row(visible=False) as demarc1:
@@ -319,7 +326,7 @@ Check out [this video]() for a quick demo of what R2P2 is, and how it can help!
             sent_pair_source2_1 = gr.Textbox(label='Sentence from Submission', visible=False)
             sent_pair_source2_1_hl = gr.components.Interpretation(sent_pair_source2_1)
         with gr.Column(scale=4):
-            sent_pair_candidate2_1 = gr.Textbox(label='Sentence from Paper', visible=False)
+            sent_pair_candidate2_1 = gr.Textbox(label="Sentence from Reviewer's Paper", visible=False)
             sent_pair_candidate2_1_hl = gr.components.Interpretation(sent_pair_candidate2_1)
     with gr.Row() as rel2_2:
         with gr.Column(scale=1):
@@ -328,7 +335,7 @@ Check out [this video]() for a quick demo of what R2P2 is, and how it can help!
             sent_pair_source2_2 = gr.Textbox(label='Sentence from Submission', visible=False)
             sent_pair_source2_2_hl = gr.components.Interpretation(sent_pair_source2_2)
         with gr.Column(scale=4):
-            sent_pair_candidate2_2 = gr.Textbox(label='Sentence from Paper', visible=False)
+            sent_pair_candidate2_2 = gr.Textbox(label="Sentence from Reviewer's Paper", visible=False)
             sent_pair_candidate2_2_hl = gr.components.Interpretation(sent_pair_candidate2_2)
             
     with gr.Row(visible=False) as demarc2:
@@ -349,7 +356,7 @@ Check out [this video]() for a quick demo of what R2P2 is, and how it can help!
             sent_pair_source3_1 = gr.Textbox(label='Sentence from Submission', visible=False)
             sent_pair_source3_1_hl = gr.components.Interpretation(sent_pair_source3_1)
         with gr.Column(scale=4):
-            sent_pair_candidate3_1 = gr.Textbox(label='Sentence from Paper', visible=False)
+            sent_pair_candidate3_1 = gr.Textbox(label="Sentence from Reviewer's Paper", visible=False)
             sent_pair_candidate3_1_hl = gr.components.Interpretation(sent_pair_candidate3_1)
     with gr.Row() as rel3_2:
         with gr.Column(scale=1):
@@ -358,51 +365,56 @@ Check out [this video]() for a quick demo of what R2P2 is, and how it can help!
             sent_pair_source3_2 = gr.Textbox(label='Sentence from Submission', visible=False)
             sent_pair_source3_2_hl = gr.components.Interpretation(sent_pair_source3_2)
         with gr.Column(scale=4):
-            sent_pair_candidate3_2 = gr.Textbox(label='Sentence from Paper', visible=False)
+            sent_pair_candidate3_2 = gr.Textbox(label="Sentence from Reviewer's Paper", visible=False)
             sent_pair_candidate3_2_hl = gr.components.Interpretation(sent_pair_candidate3_2)
 
     ## Show more button
     with gr.Row():
-        see_more_rel_btn = gr.Button('Explore more in other papers', visible=False)
+        see_more_rel_btn = gr.Button('Explore more', visible=False)
     
     ### PAPER INFORMATION
     
-    # Description
+    # Description for Explore More Section
     with gr.Row():
-        result2_desc = gr.Markdown(
-            value=''
-            ,visible=False
-        )
+        result2_desc = gr.Markdown(value='', visible=False)
+        
+    # Highlight description 
+    hl_desc = """
+    **<span style="color:black;background-color:#DB7262;">Red</span>**: sentences simiar to the selected sentence from submission. Darker = more similar.
+     
+    **<span style="color:black;background-color:#65B5E3;">Blue</span>**: phrases that appear in both sentences.
 
+    --- 
+    """
+        
     # show multiple papers in radio check box to select from
+    paper_abstract = gr.Textbox(label='Abstract', interactive=False, visible=False)
     with gr.Row():
-        selected_papers_radio = gr.Radio(
-            choices=[], # will be udpated with the button click
-            visible=False, # also will be updated with the button click
-            label='Top Relevant Papers from the Reviewer'
-        )
-    
-    # selected paper information 
-    with gr.Row(visible=False) as title_row:
-        with gr.Column(scale=3):
-            paper_title = gr.Markdown(value='')
         with gr.Column(scale=1):
-            affinity = gr.Markdown(value='')
-    with gr.Row():
-        paper_abstract = gr.Textbox(label='Abstract', interactive=False, visible=False)
-         
-    ### RELEVANT PARTS (HIGHLIGHTS)
-    with gr.Row(): 
-        with gr.Column(scale=2): # text from submission
+            selected_papers_radio = gr.Radio(
+                choices=[], # will be udpated with the button click
+                visible=False, # also will be updated with the button click
+                label='Top Relevant Papers from the Reviewer'
+            )
+        with gr.Column(scale=2):
+            # sentences from submission
             source_sentences = gr.Radio(
                 choices=[], 
                 visible=False, 
                 label='Sentences from Submission Abstract',
             )
-        with gr.Column(scale=3): # highlighted text from paper
-            highlight = gr.components.Interpretation(paper_abstract) 
-    
-    
+        with gr.Column(scale=3):
+            # selected paper and highlight
+            with gr.Row():
+                highlight_legend = gr.Markdown(value=hl_desc, visible=False)
+            with gr.Row(visible=False) as title_row:
+                paper_title = gr.Markdown(value='')
+            with gr.Row(visible=False) as aff_row:
+                affinity = gr.Markdown(value='')
+            with gr.Row(): 
+                # highlighted text from paper
+                highlight = gr.components.Interpretation(paper_abstract) 
+            
     ### EVENT LISTENERS
     
     compute_btn.click(
@@ -463,6 +475,7 @@ Check out [this video]() for a quick demo of what R2P2 is, and how it can help!
             demarc1,
             demarc2,
             search_status,
+            result2_desc,
             info,
         ],
         show_progress=True,
@@ -478,7 +491,8 @@ Check out [this video]() for a quick demo of what R2P2 is, and how it can help!
             selected_papers_radio,
             source_sentences,
             title_row,
-            paper_abstract
+            aff_row,
+            highlight_legend,
         ]
     )
     
@@ -508,14 +522,5 @@ Check out [this video]() for a quick demo of what R2P2 is, and how it can help!
         ]
     )
     
-    gr.Markdown(
-        """
-        ---------
-        **Disclaimer.** This tool and its output should not serve as the sole justification for confirming a match for the submission. It is intended as a supplementary tool that the users may use at their discretion; the correctness of the output of the tool is not guaranteed. The search results may be improved by updating the internal models used to compute the affinity scores and sentence relevance, which may require additional independent research. The tool does not compromise the privacy of the reviewers --- it relies only on their publicly-available information (e.g., names and list of previously published papers). All input information will only be temporarily used for internal computation, will not be saved externally, and will be removed when the session is refreshed or closed.
-        """
-    )
-    
 if __name__ == "__main__":
-    #demo.queue().launch(share=True) 
-    demo.queue().launch() 
-    # TODO how to disable dark mode?
+    demo.queue().launch()  # add ?__theme=light to force light mode

details.html

@@ -0,0 +1,25 @@
+<!DOCTYPE html>
+<html>
+<body>
+
+<h1>Relevant Work</h1>
+
+The tool is based on the findings from the paper <a href="https://arxiv.org/abs/2302.08450", target="_blank">Assisting Human Decisions in Document Matching</a>.
+
+<h1>What Happens Behind the Scenes</h1>
+<ul>
+    <li> The tool retrieves the reviewer's previous publications using <a href="https://www.semanticscholar.org/product/api", target="_blank">Semantic Scholar API</a>.</li>
+    <li> The tool computes the affinity score between the submission abstract and each paper's abstract, using text representations from a <a href="https://github.com/allenai/specter/tree/master/specter", target="_blank">language model fine-tuned on academic papers</a>.</li>
+    <li> The tool computes pairwise sentence relevance scores between the submission abstract and the reviewer paper's abstract, using text representations from a <a href="https://huggingface.co/sentence-transformers/gtr-t5-base", target="_blank">sentence-level langauge model</a>.</li>
+    <li> The tool highlights overlapping words (nouns) between setence pairs using <a href="https://www.nltk.org/book/ch05.html", target="_blank">POS tagging</a>.</li>
+</ul>
+
+<h1>Privacy Policy</h1>
+
+The tool does not compromise the privacy of the reviewers. It only relies only on their publicly-available information (e.g., names and list of previously published papers). All input information will only be temporarily used for internal computation, will not be saved externally, and will be deleted when the session is refreshed or closed. No search history will be kept. 
+
+<h1>Disclaimer</h1>
+
+This tool and its output should not serve as the sole justification for confirming a match for the submission. It is intended as a <b>supplementary</b> tool that the users may use at their discretion. The correctness of the output of the tool is not guaranteed. The search results may be improved by updating the internal models used to compute the affinity scores and sentence relevance, which may require additional independent research and experimentation.
+</body>
+</html> 

score.py

@@ -259,7 +259,8 @@ def predict_docscore(doc_model, tokenizer, query, titles, abstracts, batch=20):
     title_abs = []
     for t, a in zip(titles, abstracts):
         if t is not None and a is not None:
-            title_abs.append(t + ' [SEP] ' + a)    
+            # title_abs.append(t + ' [SEP] ' + a)    
+            title_abs.append(a)
             
     num_docs = len(title_abs) 
     no_iter = int(np.ceil(num_docs / batch))