import gradio as gr import os from transformers import AutoTokenizer, AutoModel from sentence_transformers import SentenceTransformer import pickle import nltk nltk.download('punkt') # tokenizer nltk.download('averaged_perceptron_tagger') # postagger import time from input_format import * from score import * # load document scoring model #torch.cuda.is_available = lambda : False # uncomment to test with CPU only device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') pretrained_model = 'allenai/specter' tokenizer = AutoTokenizer.from_pretrained(pretrained_model) doc_model = AutoModel.from_pretrained(pretrained_model) doc_model.to(device) # load sentence model sent_model = SentenceTransformer('sentence-transformers/gtr-t5-base') sent_model.to(device) def get_similar_paper( abstract_text_input, author_id_input, results={}, # this state variable will be updated and returned #progress=gr.Progress() ): progress = gr.Progress() num_papers_show = 10 # number of top papers to show from the reviewer print('retrieving similar papers...') start = time.time() input_sentences = sent_tokenize(abstract_text_input) # Get author papers from id #progress(0.1, desc="Retrieving reviewer papers ...") name, papers = get_text_from_author_id(author_id_input) # Compute Doc-level affinity scores for the Papers # print('computing document scores...') #progress(0.5, desc="Computing document scores...") # TODO detect duplicate papers? titles, abstracts, paper_urls, doc_scores = compute_document_score( doc_model, tokenizer, abstract_text_input, papers, batch=10 ) results = { 'name': name, 'titles': titles, 'abstracts': abstracts, 'urls': paper_urls, 'doc_scores': doc_scores } # Select top K choices of papers to show titles = titles[:num_papers_show] abstracts = abstracts[:num_papers_show] doc_scores = doc_scores[:num_papers_show] paper_urls = paper_urls[:num_papers_show] display_title = ['[ %0.3f ] %s'%(s, t) for t, s in zip(titles, doc_scores)] end = time.time() retrieval_time = end - start print('paper retrieval complete in [%0.2f] seconds'%(retrieval_time)) progress(0.9, desc="Obtaining relevant information from the papers...") print('obtaining highlights..') start = time.time() input_sentences = sent_tokenize(abstract_text_input) num_sents = len(input_sentences) for aa, (tt, ab, ds, url) in enumerate(zip(titles, abstracts, doc_scores, paper_urls)): # Compute sent-level and phrase-level affinity scores for each papers sent_ids, sent_scores, info, top_pairs_info = get_highlight_info( sent_model, abstract_text_input, ab, K=2 # top two sentences from the candidate ) # get scores for each word in the format for Gradio Interpretation component word_scores = dict() for i in range(num_sents): ww, ss = remove_spaces(info['all_words'], info[i]['scores']) word_scores[str(i)] = { "original": ab, "interpretation": list(zip(ww, ss)) } results[display_title[aa]] = { 'title': tt, 'abstract': ab, 'doc_score': '%0.3f'%ds, 'source_sentences': input_sentences, 'highlight': word_scores, 'top_pairs': top_pairs_info, 'url': url } end = time.time() highlight_time = end - start print('done in [%0.2f] seconds'%(highlight_time)) ## Set up output elements # 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 ] # set up elements to visualize upfront top_papers_show = 3 # number of top papers to show upfront top_num_info_show = 2 # number of sentence pairs from each paper to show upfront summary_out = [] for i in range(top_papers_show): if i == 0: out_tmp = [ gr.update(value="""

%s

"""%(paper_urls[i], titles[i]), visible=True), gr.update(value="""#### Affinity Score: %0.3f

Measures how similar the paper's abstract is to the submission abstract.

"""%doc_scores[i], visible=True) # document affinity ] else: out_tmp = [ gr.update(value="""

%s

"""%(paper_urls[i], titles[i]), visible=True), gr.update(value='#### Affinity Score: %0.3f'%doc_scores[i], visible=True) # document affinity ] tp = results[display_title[i]]['top_pairs'] for j in range(top_num_info_show): if i == 0 and j == 0: out_tmp += [ gr.update(value="""Sentence Relevance:\n%0.3f

Measures how similar the sentence pairs are.

"""%tp[j]['score'], visible=True), # sentence relevance tp[j]['query']['original'], tp[j]['query'], tp[j]['candidate']['original'], tp[j]['candidate'] ] else: out_tmp += [ gr.update(value='Sentence Relevance:\n%0.3f'%tp[j]['score'], visible=True), # sentence relevance tp[j]['query']['original'], tp[j]['query'], tp[j]['candidate']['original'], tp[j]['candidate'] ] summary_out += out_tmp # add updates to the show more button out = out + summary_out + [gr.update(visible=True)] # make show more button visible assert(len(out) == (top_num_info_show * 5 + 2) * top_papers_show + 3) out += [gr.update(value="""

Top three relevant papers by the reviewer %s

For each paper, two sentence pairs (one from the submission, one from the paper) with the highest relevance scores are shown. **Blue highlights**: phrases that appear in both sentences. """%(author_id_input, results['name']), visible=True)] # result 1 description out += [gr.update(visible=True), gr.update(visible=True)] # demarcation line between results # progress status out += [gr.update(value='Done (in %0.1f seconds)'%(retrieval_time+highlight_time), visible=True)] # add the search results to pass on to the Gradio State varaible out += [results] return tuple(out) 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), # set of papers gr.update(visible=True), # submission sentences gr.update(visible=True), # title row gr.update(visible=True), # abstract row ) def show_status(): # show search status field when search button is clicked return gr.update(visible=True) def update_name(author_id_input): # update the name of the author based on the id input name, _ = get_text_from_author_id(author_id_input) return gr.update(value=name) def change_output_highlight(selected_papers_radio, source_sent_choice, info={}): # change the output highlight based on the sentence selected from the submission if len(info.keys()) != 0: # if the info is not empty source_sents = info[selected_papers_radio]['source_sentences'] highlights = info[selected_papers_radio]['highlight'] for i, s in enumerate(source_sents): if source_sent_choice == s: return highlights[str(i)] else: return def change_paper(selected_papers_radio, info={}): if len(info.keys()) != 0: # if the info is not empty title = info[selected_papers_radio]['title'] abstract = info[selected_papers_radio]['abstract'] aff_score = info[selected_papers_radio]['doc_score'] highlights = info[selected_papers_radio]['highlight'] url = info[selected_papers_radio]['url'] title_out = """

%s

"""%(url, title) aff_score_out = '#### Affinity Score: %s'%aff_score return title_out, abstract, aff_score_out, highlights['0'] else: return with gr.Blocks(css='style.css') as demo: info = gr.State({}) # cached search results as a State variable shared throughout # 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? 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. 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! ------- """ ) ### INPUT with gr.Row() as input_row: with gr.Column(): abstract_text_input = gr.Textbox(label='Submission Abstract', info='Paste in the abstract of the submission.') with gr.Column(): with gr.Row(): author_id_input = gr.Textbox(label='Reviewer Profile Link (Semantic Scholar)', info="Paste in the reviewer's Semantic Scholar link") with gr.Row(): name = gr.Textbox(label='Confirm Reviewer Name', info='This will be automatically updated based on the reviewer profile link above', interactive=False) author_id_input.change(fn=update_name, inputs=author_id_input, outputs=name) with gr.Row(): compute_btn = gr.Button('What Makes This a Good Match?') with gr.Row(): search_status = gr.Textbox(label='Search Status', interactive=False, visible=False) ### OVERVIEW # Paper title, score, and top-ranking sentence pairs -- two sentence pairs per paper, three papers ## ONE BLOCK OF INFO FOR A SINGLE PAPER ## PAPER1 with gr.Row(): result1_desc = gr.Markdown(value='', visible=False) # TODO hovering instructions with gr.Row(): with gr.Column(scale=3): paper_title1 = gr.Markdown(value='', visible=False) with gr.Column(scale=1): affinity1 = gr.Markdown(value='', visible=False) with gr.Row() as rel1_1: with gr.Column(scale=1): sent_pair_score1_1 = gr.Markdown(interactive=False, value='', visible=False) with gr.Column(scale=4): 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_hl = gr.components.Interpretation(sent_pair_candidate1_1) with gr.Row() as rel1_2: with gr.Column(scale=1): sent_pair_score1_2 = gr.Markdown(interactive=False, value='', visible=False) with gr.Column(scale=4): 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_hl = gr.components.Interpretation(sent_pair_candidate1_2) with gr.Row(visible=False) as demarc1: gr.Markdown( """---""" ) ## PAPER 2 with gr.Row(): with gr.Column(scale=3): paper_title2 = gr.Markdown(value='', visible=False) with gr.Column(scale=1): affinity2 = gr.Markdown(value='', visible=False) with gr.Row() as rel2_1: with gr.Column(scale=1): sent_pair_score2_1 = gr.Markdown(interactive=False, value='', visible=False) with gr.Column(scale=4): 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_hl = gr.components.Interpretation(sent_pair_candidate2_1) with gr.Row() as rel2_2: with gr.Column(scale=1): sent_pair_score2_2 = gr.Markdown(interactive=False, value='', visible=False) with gr.Column(scale=4): 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_hl = gr.components.Interpretation(sent_pair_candidate2_2) with gr.Row(visible=False) as demarc2: gr.Markdown( """---""" ) ## PAPER 3 with gr.Row(): with gr.Column(scale=3): paper_title3 = gr.Markdown(value='', visible=False) with gr.Column(scale=1): affinity3 = gr.Markdown(value='', visible=False) with gr.Row() as rel3_1: with gr.Column(scale=1): sent_pair_score3_1 = gr.Markdown(interactive=False, value='', visible=False) with gr.Column(scale=4): 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_hl = gr.components.Interpretation(sent_pair_candidate3_1) with gr.Row() as rel3_2: with gr.Column(scale=1): sent_pair_score3_2 = gr.Markdown(interactive=False, value='', visible=False) with gr.Column(scale=4): 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_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) ### PAPER INFORMATION # Description with gr.Row(): result2_desc = gr.Markdown( value='' ,visible=False ) # show multiple papers in radio check box to select from 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 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) ### EVENT LISTENERS compute_btn.click( fn=show_status, inputs=[], outputs=search_status ) # retrieve similar papers and show top results compute_btn.click( fn=get_similar_paper, inputs=[ abstract_text_input, author_id_input, info ], outputs=[ selected_papers_radio, source_sentences, paper_title1, # paper info affinity1, sent_pair_score1_1, sent_pair_source1_1, sent_pair_source1_1_hl, sent_pair_candidate1_1, sent_pair_candidate1_1_hl, sent_pair_score1_2, sent_pair_source1_2, sent_pair_source1_2_hl, sent_pair_candidate1_2, sent_pair_candidate1_2_hl, paper_title2, affinity2, sent_pair_score2_1, sent_pair_source2_1, sent_pair_source2_1_hl, sent_pair_candidate2_1, sent_pair_candidate2_1_hl, sent_pair_score2_2, sent_pair_source2_2, sent_pair_source2_2_hl, sent_pair_candidate2_2, sent_pair_candidate2_2_hl, paper_title3, affinity3, sent_pair_score3_1, sent_pair_source3_1, sent_pair_source3_1_hl, sent_pair_candidate3_1, sent_pair_candidate3_1_hl, sent_pair_score3_2, sent_pair_source3_2, sent_pair_source3_2_hl, sent_pair_candidate3_2, sent_pair_candidate3_2_hl, see_more_rel_btn, result1_desc, demarc1, demarc2, search_status, info, ], show_progress=True, scroll_to_output=True ) # Get more info (move to more interactive portion) see_more_rel_btn.click( fn=show_more, inputs=info, outputs=[ result2_desc, selected_papers_radio, source_sentences, title_row, paper_abstract ] ) # change highlight based on selected sentences from submission source_sentences.change( fn=change_output_highlight, inputs=[ selected_papers_radio, source_sentences, info ], outputs=highlight ) # change paper to show based on selected papers selected_papers_radio.change( fn=change_paper, inputs=[ selected_papers_radio, info, ], outputs= [ paper_title, paper_abstract, affinity, highlight ] ) 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?