{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/improved-grammatical-error-correction-by","title":"Improved grammatical error correction by ranking elementary edits","arxiv_id":null,"date":"2021-11-16","proceeding":"ACL ARR November 2021 11","authors":["Anonymous"],"abstract":"We offer a rescoring method for grammatical error correction which is based on two-stage procedure: the first stage model extracts local edits and the second classiifies them as correct or false. We show how to use an encoder-decoder or sequence labeling approach as the first stage of our model. We achieve state-of-the-art quality on BEA 2019 English dataset even with a weak BERT-GEC basic model. When using a state-of-the-art GECToR edit generator and the combined scorer, our model beats GECToR on BEA 2019 by $2-3\\%$. Our model also beats previous state-of-the-art on Russian, despite using smaller models and less data than the previous approaches.","url_abs":"https://openreview.net/forum?id=bg470UXkLqF","url_pdf":"https://openreview.net/pdf?id=bg470UXkLqF","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":"improved-grammatical-error-correction-by","repo_url":"https://github.com/AlexeySorokin/EditScorer","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"grammatical-error-correction","task_name":"Grammatical Error Correction"}],"methods":[{"method_slug":"cross-encoder-reranking","method_name":"Cross-encoder Reranking"},{"method_slug":"roberta","method_name":"RoBERTa"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/grammatical-error-correction-on-bea-2019-test","task":"Grammatical Error Correction","dataset":"BEA-2019 (test)","model":"clang_large_ft2-gector","rank_in_archive_order":5,"of":19,"metrics":{"F0.5":"77.1"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}