added text instructions at the top; input now accepts semantic scholar profile link instead of the numeric id

app.py

@@ -150,6 +150,34 @@ def change_paper(selected_papers_radio):
 
 with gr.Blocks() as demo:
     
+    # TODO Text description about the app and disclaimer
+    ### TEXT Description
+    gr.Markdown(
+        """
+# Paper Matching Helper
+
+This is a tool designed to help match an academic paper (submission) to a potential peer reviewer, by presenting information that may be relevant to the users.
+Below we describe how to use the tool. Also feel free to check out the [video]() for a more detailed rundown. 
+
+##### Input
+- The tool requires two inputs: (1) an academic paper's abstract in 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" 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). 
+- It will list top 10 similar papers along with the affinity score (ranging from 0 -1), 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 on the "Show Relevant Parts" button.
+- 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:red">Red</span> highlights: sentences from the reviewer's paper abstract with high semantic similarity to the selected sentence.
+- <span style="color:blue">Blue</span> highlights: matching 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 the paper above and re-click "Show Relevant Parts" to refresh. 
+
+**Disclaimer.** This tool and its output should not serve as a 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). 
+        """
+    ) 
+    
     ### INPUT
     with gr.Row() as input_row:
         with gr.Column():
@@ -158,7 +186,7 @@ with gr.Blocks() as demo:
             pdf_file_input = gr.File(label='OR upload a submission PDF File')
         with gr.Column():
             with gr.Row():
-                author_id_input = gr.Textbox(label='Reviewer ID (Semantic Scholar)')
+                author_id_input = gr.Textbox(label='Reviewer Link or ID (Semantic Scholar)')
             with gr.Row():
                 name = gr.Textbox(label='Confirm Reviewer Name', interactive=False)
                 author_id_input.change(fn=update_name, inputs=author_id_input, outputs=name)

input_format.py

@@ -69,12 +69,14 @@ def download_pdf(url, file_name):
 def get_text_from_author_id(author_id, max_count=100):
     if author_id is None:
         raise ValueError('Input valid author ID')
-    author_id = str(author_id)
-#     author_id = '1737249'
-    url = "https://api.semanticscholar.org/graph/v1/author/%s?fields=url,name,paperCount,papers,papers.title,papers.abstract"%author_id
+    aid = str(author_id)
+    if 'http' in aid: # handle semantic scholar url input
+        aid = aid.split('/')
+        aid = aid[aid.index('author')+2]
+    url = "https://api.semanticscholar.org/graph/v1/author/%s?fields=url,name,paperCount,papers,papers.title,papers.abstract"%aid
     r = requests.get(url)
     if r.status_code == 404:
-        raise ValueError('Input valid author ID')
+        raise ValueError('Author link not found.')
     data = r.json()
     papers = data['papers'][:max_count]
     name = data['name']

requirements.txt

@@ -13,3 +13,4 @@ sentence-transformers==2.2.0
 torch==1.9.0
 transformers
 urllib3==1.26.6
+tqdm

score.py

@@ -3,6 +3,7 @@ from nltk.tokenize import sent_tokenize
 from nltk import word_tokenize, pos_tag
 import torch
 import numpy as np
+import tqdm
 
 def compute_sentencewise_scores(model, query_sents, candidate_sents):
     # TODO make this more general for different types of models
@@ -161,7 +162,7 @@ def predict_docscore(doc_model, tokenizer, query, titles, abstracts, batch=20):
     scores = []
     with torch.no_grad():
         # batch
-        for i in range(no_iter):
+        for i in tqdm.tqdm(range(no_iter)):
             # preprocess the input
             inputs = tokenizer(
                 [query] + title_abs[i*batch:(i+1)*batch],