{"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/neural-quality-estimation-with-multiple","title":"Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correction","arxiv_id":"2105.04443","date":"2021-05-10","proceeding":"NAACL 2021 4","authors":["Zhenghao Liu","Xiaoyuan Yi","Maosong Sun","Liner Yang","Tat-Seng Chua"],"abstract":"Grammatical Error Correction (GEC) aims to correct writing errors and help language learners improve their writing skills. However, existing GEC models tend to produce spurious corrections or fail to detect lots of errors. The quality estimation model is necessary to ensure learners get accurate GEC results and avoid misleading from poorly corrected sentences. Well-trained GEC models can generate several high-quality hypotheses through decoding, such as beam search, which provide valuable GEC evidence and can be used to evaluate GEC quality. However, existing models neglect the possible GEC evidence from different hypotheses. This paper presents the Neural Verification Network (VERNet) for GEC quality estimation with multiple hypotheses. VERNet establishes interactions among hypotheses with a reasoning graph and conducts two kinds of attention mechanisms to propagate GEC evidence to verify the quality of generated hypotheses. Our experiments on four GEC datasets show that VERNet achieves state-of-the-art grammatical error detection performance, achieves the best quality estimation results, and significantly improves GEC performance by reranking hypotheses. All data and source codes are available at https://github.com/thunlp/VERNet.","url_abs":"https://arxiv.org/abs/2105.04443v1","url_pdf":"https://arxiv.org/pdf/2105.04443v1.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":"neural-quality-estimation-with-multiple","repo_url":"https://github.com/thunlp/VERNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"grammatical-error-correction","task_name":"Grammatical Error Correction"},{"task_slug":"grammatical-error-detection","task_name":"Grammatical Error Detection"},{"task_slug":"reranking","task_name":"Reranking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/grammatical-error-correction-on-bea-2019-test","task":"Grammatical Error Correction","dataset":"BEA-2019 (test)","model":"VERNet","rank_in_archive_order":18,"of":19,"metrics":{"F0.5":"68.9"},"uses_additional_data":false},{"leaderboard":"/sota/grammatical-error-correction-on-conll-2014","task":"Grammatical Error Correction","dataset":"CoNLL-2014 Shared Task","model":"VERNet","rank_in_archive_order":15,"of":23,"metrics":{"F0.5":"63.7"},"uses_additional_data":false},{"leaderboard":"/sota/grammatical-error-correction-on-jfleg","task":"Grammatical Error Correction","dataset":"JFLEG","model":"VERNet","rank_in_archive_order":1,"of":6,"metrics":{"GLEU":"62.1"},"uses_additional_data":false},{"leaderboard":"/sota/grammatical-error-detection-on-conll-2014-a1","task":"Grammatical Error Detection","dataset":"CoNLL-2014 A1","model":"VERNet","rank_in_archive_order":1,"of":8,"metrics":{"F0.5":"54.3"},"uses_additional_data":false},{"leaderboard":"/sota/grammatical-error-detection-on-conll-2014-a2","task":"Grammatical Error Detection","dataset":"CoNLL-2014 A2","model":"VERNet","rank_in_archive_order":1,"of":8,"metrics":{"F0.5":"63.1"},"uses_additional_data":false},{"leaderboard":"/sota/grammatical-error-detection-on-fce","task":"Grammatical Error Detection","dataset":"FCE","model":"VERNet","rank_in_archive_order":1,"of":8,"metrics":{"F0.5":"72.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2105.04443","atlas_url":"https://app.syntology.ai/?focus=2105.04443","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":"2105.04443"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2105.04443\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2105.04443"},"call":"get_concepts_for_paper(arxiv_id=\"2105.04443\")"}],"by_repo":[{"repo":"thunlp/VERNet","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":"a5f21d84ff91eb808d549cd33597516721fe4304f30ea02397ba6296e6db7846","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}