adding null check for papers retrieved; made relevant parts pop up without additional refresh button step

app.py

@@ -43,7 +43,8 @@ def get_similar_paper(
         name, papers = get_text_from_author_id(author_id_input)
     
     # Compute Doc-level affinity scores for the Papers 
-    print('computing scores...')
+    print('computing scores...') 
+    # TODO detect duplicate papers?
     titles, abstracts, doc_scores = compute_document_score(
         doc_model, 
         tokenizer,
@@ -57,7 +58,6 @@ def get_similar_paper(
         'abstracts': abstracts,
         'doc_scores': doc_scores
     }
-    pickle.dump(tmp, open('paper_info.pkl', 'wb'))
     
     # Select top K choices of papers to show
     titles = titles[:num_papers_show]
@@ -66,54 +66,47 @@ def get_similar_paper(
     
     display_title = ['[ %0.3f ] %s'%(s, t) for t, s in zip(titles, doc_scores)]
     end = time.time()
-    print('retrieval complete in [%0.2f] seconds'%(end - start))
+    print('paper retrieval complete in [%0.2f] seconds'%(end - start))
     
-    return (
-        gr.update(choices=display_title, interactive=True, visible=True), # set of papers
-        gr.update(choices=input_sentences, interactive=True), # submission sentences
-        gr.update(visible=True),    # title row
-        gr.update(visible=True),    # abstract row
-        gr.update(visible=True)     # button
-    )
-
-def get_highlights(
-    abstract_text_input,
-    pdf_file_input,
-    abstract,
-    K=2
-):
     print('obtaining highlights..')
     start = time.time()
-    # Compute sent-level and phrase-level affinity scores for each papers
-    sent_ids, sent_scores, info = get_highlight_info(
-        sent_model, 
-        abstract_text_input, 
-        abstract,
-        K=K
-    )
-
     input_sentences = sent_tokenize(abstract_text_input)
     num_sents = len(input_sentences)
-     
-    word_scores = dict()
-    
-    # different highlights for each input sentence
-    for i in range(num_sents):
-        word_scores[str(i)] = {
-            "original": abstract,
-            "interpretation": list(zip(info['all_words'], info[i]['scores']))
-        } # format to feed to for Gradio Interpretation component
-    
-    tmp = {
-        'source_sentences': input_sentences,
-        'highlight': word_scores
-    }
-    pickle.dump(tmp, open('highlight_info.pkl', 'wb'))
+    for aa, (tt, ab, ds) in enumerate(zip(titles, abstracts, doc_scores)):
+        # Compute sent-level and phrase-level affinity scores for each papers
+        sent_ids, sent_scores, info = get_highlight_info(
+            sent_model, 
+            abstract_text_input, 
+            ab,
+            K=2
+        )
+
+        word_scores = dict()
+        
+        # different highlights for each input sentence
+        for i in range(num_sents):
+            word_scores[str(i)] = {
+                "original": ab,
+                "interpretation": list(zip(info['all_words'], info[i]['scores']))
+            } # format to feed to for Gradio Interpretation component
+
+        tmp[display_title[aa]] = {
+            'title': tt,
+            'abstract': ab,
+            'doc_score': ds,
+            'source_sentences': input_sentences,
+            'highlight': word_scores
+        }
+    pickle.dump(tmp, open('info.pkl', 'wb'))  # TODO better ways of saving intermediate results?
     end = time.time()
     print('done in [%0.2f] seconds'%(end - start))
     
-    # update the visibility of radio choices
-    return gr.update(visible=True)
+    return (
+        gr.update(choices=display_title, interactive=True, visible=True), # set of papers
+        gr.update(choices=input_sentences, interactive=True, visible=True), # submission sentences
+        gr.update(visible=True),    # title row
+        gr.update(visible=True),    # abstract row
+    )
 
 def update_name(author_id_input):
     # update the name of the author based on the id input
@@ -121,13 +114,13 @@ def update_name(author_id_input):
     
     return gr.update(value=name)
 
-def change_output_highlight(source_sent_choice):
+def change_output_highlight(selected_papers_radio, source_sent_choice):
     # change the output highlight based on the sentence selected from the submission
-    fname = 'highlight_info.pkl'
+    fname = 'info.pkl'
     if os.path.exists(fname):
         tmp = pickle.load(open(fname, 'rb'))
-        source_sents = tmp['source_sentences']
-        highlights = tmp['highlight']
+        source_sents = tmp[selected_papers_radio]['source_sentences']
+        highlights = tmp[selected_papers_radio]['highlight']
         for i, s in enumerate(source_sents):
             #print('changing highlight')
             if source_sent_choice == s:
@@ -137,14 +130,15 @@ def change_output_highlight(source_sent_choice):
 
 def change_paper(selected_papers_radio):
     # change the paper to show based on the paper selected
-    fname = 'paper_info.pkl'
+    fname = 'info.pkl'
     if os.path.exists(fname):
         tmp = pickle.load(open(fname, 'rb'))
-        for title, abstract, aff_score in zip(tmp['titles'], tmp['abstracts'], tmp['doc_scores']):
-            display_title = '[ %0.3f ] %s'%(aff_score, title)
-            if display_title == selected_papers_radio:
-                #print('changing paper')
-                return title, abstract, aff_score   # update title, abstract, and affinity score fields
+        title = tmp[selected_papers_radio]['title']
+        abstract = tmp[selected_papers_radio]['abstract']
+        aff_score = tmp[selected_papers_radio]['doc_score']
+        highlights = tmp[selected_papers_radio]['highlight']
+        return title, abstract, aff_score, highlights['0']
+
     else:
         return
 
@@ -162,18 +156,19 @@ Below we describe how to use the tool. Also feel free to check out the [video]()
 
 ##### Input
 - The tool requires two inputs: (1) an academic paper's abstract in a text format, (2) and a potential reviewer's [Semantic Scholar](https://www.semanticscholar.org/) profile link. Once you put in a valid profile link, the reviewer's name will be displayed. 
-- Once the name is confirmed, press the `Search Similar Papers from the Reviewer` button.
-##### Search Similar Papers
-- Based on the input information above, the tool will search for similar papers from the reviewer's previous publications using [Semantic Scholar API](https://www.semanticscholar.org/product/api). 
+- Once the name is confirmed, press the `What Makes this a Good Match?` button.
+##### Similar Papers From the Reviewer
+- Based on the input information above, the tool will first search for similar papers from the reviewer's previous publications using [Semantic Scholar API](https://www.semanticscholar.org/product/api). 
 - It will list top 10 similar papers along with the **affinity scores** (ranging from 0 -1) for each, computed using text representations from a [language model](https://github.com/allenai/specter/tree/master/specter).
 - You can click on different papers to see title, abstract, and affinity scores in detail. 
-##### Show Relevant Parts
-- Once you have retrieved the similar papers above, and selected a paper that you are interested in, you will have an option to see what parts of the selected paper may be relevant to the submission abstract. Click `Show Relevant Parts from Selected Paper` button.
+##### Relevant Parts
+- Below the list of papers, we highlight relevant parts in the selected paper compared to the submission abstract.
 - On the left, you will see individual sentences from the submission abstract you can select from.
 - On the right, you will see the abstract of the selected paper, with **highlights**.
 - **<span style="color:black;background-color:#DB7262;">Red highlights</span>**: sentences from the reviewer's paper abstract with high semantic similarity to the selected sentence.
 - **<span style="color:black;background-color:#5296D5;">Blue highlights</span>**: phrases from the reviewer's paper abstract that is included in the selected sentence.
-- To see relevant parts in a different paper from the reviewer, select another paper above and re-click `Show Relevant Parts from Selected Paper` button to refresh. 
+- To see relevant parts in a different paper from the reviewer, select the new paper.
+-------
         """
     ) 
     
@@ -190,7 +185,7 @@ Below we describe how to use the tool. Also feel free to check out the [video]()
                 name = gr.Textbox(label='Confirm Reviewer Name', interactive=False)
                 author_id_input.change(fn=update_name, inputs=author_id_input, outputs=name)
     with gr.Row():
-        compute_btn = gr.Button('Search Similar Papers from the Reviewer')  
+        compute_btn = gr.Button('What Makes This a Good Match?')  
     
     ### PAPER INFORMATION
      
@@ -199,7 +194,7 @@ Below we describe how to use the tool. Also feel free to check out the [video]()
         selected_papers_radio = gr.Radio(
             choices=[], # will be udpated with the button click
             visible=False, # also will be updated with the button click
-            label='Selected Top Papers from the Reviewer'
+            label='Top Relevant Papers from the Reviewer'
         )
     
     # selected paper information 
@@ -208,14 +203,12 @@ Below we describe how to use the tool. Also feel free to check out the [video]()
             paper_title = gr.Textbox(label='Title', interactive=False)
         with gr.Column(scale=1):
             affinity= gr.Number(label='Affinity', interactive=False, value=0)
-    with gr.Row(visibe=False) as abstract_row:
+    with gr.Row():
         paper_abstract = gr.Textbox(label='Abstract', interactive=False, visible=False)
         
-    with gr.Row(visible=False) as explain_button_row:
-        explain_btn = gr.Button('Show Relevant Parts from Selected Paper')
-    
+    ## TODO consider adding more direct information feeding to the users before giving them options for interactions.
+ 
     ### RELEVANT PARTS (HIGHLIGHTS)
-    
     with gr.Row(): 
         with gr.Column(scale=2): # text from submission
             source_sentences = gr.Radio(
@@ -240,26 +233,17 @@ Below we describe how to use the tool. Also feel free to check out the [video]()
             selected_papers_radio,
             source_sentences,
             title_row,
-            paper_abstract,
-            explain_button_row,
+            paper_abstract
         ]
     )      
     
-    # get highlights
-    explain_btn.click(
-        fn=get_highlights,
-        inputs=[
-            abstract_text_input, 
-            pdf_file_input,
-            paper_abstract
-        ],
-        outputs=source_sentences
-    )
-    
     # change highlight based on selected sentences from submission
     source_sentences.change(
         fn=change_output_highlight,
-        inputs=source_sentences,
+        inputs=[
+            selected_papers_radio,
+            source_sentences
+        ],
         outputs=highlight
     )
     
@@ -270,7 +254,8 @@ Below we describe how to use the tool. Also feel free to check out the [video]()
         outputs= [
             paper_title,
             paper_abstract,
-            affinity
+            affinity,
+            highlight
         ]
     )
     
@@ -280,6 +265,6 @@ Below we describe how to use the tool. Also feel free to check out the [video]()
         **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 user may use at their discretion; the correctness of the output of the tool is not guaranteed. This may be improved by updating the internal models used to compute the affinity scores and sentence relevance, which may require additional research independently. The tool does not compromise the privacy of the reviewers as it relies only on their publicly-available information (e.g., names and list of previously published papers). 
         """
     )
-
+    
 if __name__ == "__main__":
     demo.launch() 

score.py

@@ -183,9 +183,11 @@ def compute_document_score(doc_model, tokenizer, query, papers, batch=5):
     titles = []
     abstracts = []
     for p in papers:
-        titles.append(p['title'])
-        abstracts.append(p['abstract'])
+        if p['title'] is not None and p['abstract'] is not None:
+            titles.append(p['title'])
+            abstracts.append(p['abstract'])
     scores = predict_docscore(doc_model, tokenizer, query, titles, abstracts, batch=batch)
+    assert(len(scores) == len(abstracts))
     idx_sorted = np.argsort(scores)[::-1]
     
     titles_sorted = [titles[x] for x in idx_sorted]