{"id":24064332,"url":"https://github.com/nusnlp/ugec","last_synced_at":"2026-01-31T21:38:53.147Z","repository":{"id":217625593,"uuid":"703014116","full_name":"nusnlp/ugec","owner":"nusnlp","description":"The official code for the \"Unsupervised Grammatical Error Correction Rivaling Supervised Methods\" paper, published in EMNLP 2023.","archived":false,"fork":false,"pushed_at":"2025-12-14T00:59:59.000Z","size":5438,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-12-15T22:26:48.851Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://aclanthology.org/2023.emnlp-main.185.pdf","language":"Python","has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/nusnlp.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-10-10T12:39:25.000Z","updated_at":"2025-12-14T01:00:07.000Z","dependencies_parsed_at":"2024-12-08T04:27:53.058Z","dependency_job_id":null,"html_url":"https://github.com/nusnlp/ugec","commit_stats":null,"previous_names":["nusnlp/ugec"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/nusnlp/ugec","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nusnlp%2Fugec","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nusnlp%2Fugec/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nusnlp%2Fugec/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nusnlp%2Fugec/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nusnlp","download_url":"https://codeload.github.com/nusnlp/ugec/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nusnlp%2Fugec/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28956343,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-31T18:30:42.805Z","status":"ssl_error","status_checked_at":"2026-01-31T18:30:19.593Z","response_time":128,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-01-09T10:24:38.002Z","updated_at":"2026-01-31T21:38:53.125Z","avatar_url":"https://github.com/nusnlp.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Unsupervised Grammatical Error Correction Rivaling Supervised Methods\n\n\u003e Hannan Cao, Liping Yuan, Yuchen Zhang, Hwee Tou Ng. [Unsupervised Grammatical Error Correction Rivaling Supervised Methods](https://aclanthology.org/2023.emnlp-main.185.pdf). In EMNLP 2023. \n\n## Training Data \u0026 Checkpoints\n[GEC training data](https://drive.google.com/drive/folders/1c1xNjD7ORGaY9P3vuy1w-q_f60WkGC_D?usp=sharing);\n[GEC model checkpoints](https://drive.google.com/drive/folders/1TZNbuEwjifTVqKldfpkXl264CLkHNlXw?usp=sharing);\n## English GEC\n\n### Flan-T5-xxl\n1. Please store all the downloaded checkpoint and data for Flan-T5-xxl in this folder: en_flan_t5/llm_finetune\n2. Install the requirement.txt inside en_flan_t5 folder\n\nTrain:\n```\nbash train.sh\n```\nInference: go to en_flan_t5/llm_inference folder\n```\nbash eval_gec.sh your/ckpt/name\n```\n### BART-base\n1. Please store all the downloaded checkpoint and data for BART-base in this folder: en_fairseq_train\n2. Install the requirement.txt inside en_fairseq_train folder\n\nTrain:\n```\ncd gec\nbash train.sh path/to/the/model/to/be/restored path/to/data-bin/folder output_path\n```\nInference:\n```\nbash new_generate.sh path/to/model/ckpt testing/input/path\n```\n## Chinese GEC\n1. Please store all the downloaded checkpoint and data for BART-base in this folder: chinese_bart_large\n2. Install the requirement.txt inside chinese_bart_large folder\n\nTrain:\n```\ncd gec\nbash train_ch.sh\n```\nInference:\n```\ncd gec\nbash test_ch.sh\n```\n## Citation\n\nIf you found our paper or code useful, please cite as:\n\n```\n@inproceedings{cao-etal-2023-unsupervised,\n    title = \"Unsupervised Grammatical Error Correction Rivaling Supervised Methods\",\n    author = \"Cao, Hannan  and\n      Yuan, Liping  and\n      Zhang, Yuchen  and\n      Ng, Hwee Tou\",\n    editor = \"Bouamor, Houda  and\n      Pino, Juan  and\n      Bali, Kalika\",\n    booktitle = \"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing\",\n    month = dec,\n    year = \"2023\",\n    address = \"Singapore\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2023.emnlp-main.185\",\n    doi = \"10.18653/v1/2023.emnlp-main.185\",\n    pages = \"3072--3088\",\n}\n```\n\nIf you encounter any problem with the code, please contact caoh@u.nus.edu .\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnusnlp%2Fugec","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnusnlp%2Fugec","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnusnlp%2Fugec/lists"}