{"id":37609109,"url":"https://github.com/yzhangcs/ctc-copy","last_synced_at":"2026-01-16T10:16:30.509Z","repository":{"id":200247341,"uuid":"701985696","full_name":"yzhangcs/ctc-copy","owner":"yzhangcs","description":"[EMNLP'23] Code for \"Non-autoregressive Text Editing with Copy-aware Latent Alignments\".","archived":false,"fork":false,"pushed_at":"2023-10-17T17:46:47.000Z","size":52,"stargazers_count":9,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2023-10-17T18:50:51.179Z","etag":null,"topics":["ctc","non-autoregressive","text-editing"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2310.07821","language":"Python","has_issues":true,"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/yzhangcs.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}},"created_at":"2023-10-08T06:46:04.000Z","updated_at":"2023-10-17T14:16:59.000Z","dependencies_parsed_at":null,"dependency_job_id":"44ae8469-06cb-46f2-bc4b-66146568e401","html_url":"https://github.com/yzhangcs/ctc-copy","commit_stats":null,"previous_names":["yzhangcs/ctc-copy"],"tags_count":0,"template":null,"template_full_name":null,"purl":"pkg:github/yzhangcs/ctc-copy","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yzhangcs%2Fctc-copy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yzhangcs%2Fctc-copy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yzhangcs%2Fctc-copy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yzhangcs%2Fctc-copy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yzhangcs","download_url":"https://codeload.github.com/yzhangcs/ctc-copy/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yzhangcs%2Fctc-copy/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28478049,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-16T06:30:42.265Z","status":"ssl_error","status_checked_at":"2026-01-16T06:30:16.248Z","response_time":107,"last_error":"SSL_read: 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":["ctc","non-autoregressive","text-editing"],"created_at":"2026-01-16T10:16:29.869Z","updated_at":"2026-01-16T10:16:30.498Z","avatar_url":"https://github.com/yzhangcs.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\n# Non-autoregressive Text Editing with Copy-aware Latent Alignments\n\n\u003cdiv\u003e\n  \u003ca href='https://yzhang.site/' target='_blank'\u003e\u003cb\u003eYu Zhang\u003c/b\u003e\u003c/a\u003e\u003csup\u003e1*\u003c/sup\u003e\u0026emsp;\n  \u003ca href='https://hillzhang1999.github.io/' target='_blank'\u003eYue Zhang\u003c/a\u003e\u003csup\u003e1*\u003c/sup\u003e\u0026emsp;\n  \u003ca href='https://nealcly.github.io/' target='_blank'\u003eLeyang Cui\u003c/b\u003e\u003c/a\u003e\u003csup\u003e2\u003c/sup\u003e\u0026emsp;\n  \u003ca href='https://web.suda.edu.cn/ghfu/' target='_blank'\u003eGuohong Fu\u003c/a\u003e\u003csup\u003e1\u003c/sup\u003e\u0026emsp;\n\u003c/div\u003e\n\u003cdiv\u003e\u003csup\u003e1\u003c/sup\u003eSoochow University, Suzhou, China\u003c/div\u003e\n\u003cdiv\u003e\u003csup\u003e2\u003c/sup\u003eTencent AI Lab\u003c/div\u003e\n\n\u003cdiv\u003e\n\u003ch4\u003e\n\n[![conf](https://img.shields.io/badge/EMNLP%202023-orange?style=flat-square)](https://yzhang.site/assets/pubs/emnlp/2023/ctc.pdf)\n[![arxiv](https://img.shields.io/badge/arXiv-2310.07821-b31b1b.svg?style=flat-square)](https://arxiv.org/abs/2310.07821)\n[![citation](https://img.shields.io/badge/dynamic/json?label=citation\u0026query=citationCount\u0026url=https%3A%2F%2Fapi.semanticscholar.org%2Fgraph%2Fv1%2Fpaper%2F116277fd27c97d50bba2d8023d3c590c1ea8187b%3Ffields%3DcitationCount\u0026style=flat-square)](https://www.semanticscholar.org/paper/Non-autoregressive-Text-Editing-with-Copy-aware-Zhang-Zhang/116277fd27c97d50bba2d8023d3c590c1ea8187b)\n![python](https://img.shields.io/badge/python-%3E%3D%203.7-pybadges.svg?logo=python\u0026style=flat-square)\n\n\u003c/h4\u003e\n\u003c/div\u003e\n\n\u003cimg width=\"400\" alt=\"image\" src=\"https://github.com/yzhangcs/ctc-copy/assets/18402347/eb3ff302-aa3a-47b5-983f-2d7b6b4f4370\"\u003e\n\n\u003c/div\u003e\n\n## Citation\n\nIf you are interested in our work, please cite\n```bib\n@inproceedings{zhang-etal-2023-ctc,\n  title     = {Non-autoregressive Text Editing with Copy-aware Latent Alignments},\n  author    = {Zhang, Yu  and\n               Zhang, Yue  and\n               Cui, Leyang  and\n               Fu, Guohong},\n  booktitle = {Proceedings of EMNLP},\n  year      = {2023},\n  address   = {Singapore}\n}\n```\n\n## Setup\n\nThe following packages should be installed:\n* [`PyTorch`](https://github.com/pytorch/pytorch): \u003e= 2.0\n* [`Transformers`](https://github.com/huggingface/transformers)\n* [`Errant`](https://github.com/chrisjbryant/errant)\n\nClone this repo recursively:\n```sh\ngit clone https://github.com/yzhangcs/ctc-copy.git --recursive\n```\n\nYou can follow this [repo](https://github.com/HillZhang1999/SynGEC) to obtain the 3-stage train/dev/test data for training a English GEC model.\nThe multilingual datasets are available [here](https://github.com/google-research-datasets/clang8).\n\nBefore running, you are required to preprocess each sentence pair into the format of `SRC:\\t[src]\\nTGT:\\t[tgt]\\n`, where `src` and `tgt` are the source and target sentences, respectively. Each sentence pair is separated by a blank line.\nSee [`data/clang8.toy`](data/clang8.toy) for examples.\n\n## Run\n\nTry the following command to train a 3-stage English model,\n```sh\nbash train.sh\n```\nTo make predictions \u0026 evaluations:\n```sh\nbash pred.sh\n```\n\n## Contact\n\nIf you have any questions, please feel free to [email](mailto:yzhang.cs@outlook.com) me.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyzhangcs%2Fctc-copy","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyzhangcs%2Fctc-copy","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyzhangcs%2Fctc-copy/lists"}