{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/fact-based-text-editing-1","title":"Fact-based Text Editing","arxiv_id":"2007.00916","date":"2020-07-02","proceeding":"ACL 2020 6","authors":["Hayate Iso","chao qiao","Hang Li"],"abstract":"We propose a novel text editing task, referred to as \\textit{fact-based text editing}, in which the goal is to revise a given document to better describe the facts in a knowledge base (e.g., several triples). The task is important in practice because reflecting the truth is a common requirement in text editing. First, we propose a method for automatically generating a dataset for research on fact-based text editing, where each instance consists of a draft text, a revised text, and several facts represented in triples. We apply the method into two public table-to-text datasets, obtaining two new datasets consisting of 233k and 37k instances, respectively. Next, we propose a new neural network architecture for fact-based text editing, called \\textsc{FactEditor}, which edits a draft text by referring to given facts using a buffer, a stream, and a memory. A straightforward approach to address the problem would be to employ an encoder-decoder model. Our experimental results on the two datasets show that \\textsc{FactEditor} outperforms the encoder-decoder approach in terms of fidelity and fluency. The results also show that \\textsc{FactEditor} conducts inference faster than the encoder-decoder approach.","url_abs":"https://arxiv.org/abs/2007.00916v1","url_pdf":"https://arxiv.org/pdf/2007.00916v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fact-based-text-editing-1","repo_url":"https://github.com/isomap/factedit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"fact-based-text-editing","task_name":"Fact-based Text Editing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/fact-based-text-editing-on-rotoedit","task":"Fact-based Text Editing","dataset":"RotoEdit","model":"FactEditor","rank_in_archive_order":1,"of":1,"metrics":{"ADD":"41.5","BLEU":"84.43","DELETE":"84.24","Exact Match":"2.65","F1":"63.39","KEEP":"98.41","Precision":"78.84","Recall":"52.3","SARI":"74.72"},"uses_additional_data":false},{"leaderboard":"/sota/fact-based-text-editing-on-webedit","task":"Fact-based Text Editing","dataset":"WebEdit","model":"FactEditor","rank_in_archive_order":1,"of":5,"metrics":{"ADD":"47.69","BLEU":"75.68","DELETE":"0.7707","Exact Match":"24.8","F1":"93.17","KEEP":"0.9184","Precision":"96.88","Recall":"89.74","SARI":"72.2"},"uses_additional_data":false},{"leaderboard":"/sota/fact-based-text-editing-on-webedit","task":"Fact-based Text Editing","dataset":"WebEdit","model":"EncDecEditor","rank_in_archive_order":2,"of":5,"metrics":{"ADD":"43.82","BLEU":"71.03","DELETE":"0.7548","Exact Match":"20.96","F1":"92.51","KEEP":"0.8949","Precision":"98.06","Recall":"87.56","SARI":"69.59"},"uses_additional_data":false},{"leaderboard":"/sota/fact-based-text-editing-on-webedit","task":"Fact-based Text Editing","dataset":"WebEdit","model":"Table-to-Text","rank_in_archive_order":3,"of":5,"metrics":{"ADD":"27.86","BLEU":"33.75","DELETE":"0.5219","Exact Match":"5.78","F1":"90.4","KEEP":"0.5144","Precision":"98.23","Recall":"83.72","SARI":"43.83"},"uses_additional_data":false},{"leaderboard":"/sota/fact-based-text-editing-on-webedit","task":"Fact-based Text Editing","dataset":"WebEdit","model":"Text-to-Text","rank_in_archive_order":4,"of":5,"metrics":{"ADD":"25.77","BLEU":"63.61","DELETE":"0.678","Exact Match":"6.22","F1":"79.48","KEEP":"0.8262","Precision":"81.93","Recall":"77.16","SARI":"58.73"},"uses_additional_data":false},{"leaderboard":"/sota/fact-based-text-editing-on-webedit","task":"Fact-based Text Editing","dataset":"WebEdit","model":"No-Editing","rank_in_archive_order":5,"of":5,"metrics":{"ADD":"3.91","BLEU":"66.67","DELETE":"0.1202","Exact Match":"0","F1":"80.21","KEEP":"0.7862","Precision":"84.49","Recall":"76.34","SARI":"31.51"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2007.00916","atlas_url":"https://app.syntology.ai/?focus=2007.00916","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2007.00916"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2007.00916\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2007.00916"},"call":"get_concepts_for_paper(arxiv_id=\"2007.00916\")"}],"by_repo":[{"repo":"isomap/factedit","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"16e2abcfab0459efbe6be0c3b7f26a134056c4c5f8e17f91010fef8c3cf93a81","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}