{"id":16269256,"url":"https://github.com/thinkwee/eda_zh_bert","last_synced_at":"2025-09-14T15:30:21.602Z","repository":{"id":79907386,"uuid":"198803532","full_name":"thinkwee/eda_zh_bert","owner":"thinkwee","description":"Chinese version code for the paper \"EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks\"","archived":false,"fork":false,"pushed_at":"2019-07-25T09:50:32.000Z","size":8,"stargazers_count":11,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-12-29T13:24:10.161Z","etag":null,"topics":["augmentation","bert","chinese-nlp","eda","nlp","nlp-toolkit"],"latest_commit_sha":null,"homepage":"","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/thinkwee.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":"2019-07-25T09:44:10.000Z","updated_at":"2024-02-18T04:58:28.000Z","dependencies_parsed_at":"2023-05-04T14:31:12.371Z","dependency_job_id":null,"html_url":"https://github.com/thinkwee/eda_zh_bert","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thinkwee%2Feda_zh_bert","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thinkwee%2Feda_zh_bert/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thinkwee%2Feda_zh_bert/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thinkwee%2Feda_zh_bert/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/thinkwee","download_url":"https://codeload.github.com/thinkwee/eda_zh_bert/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":233659837,"owners_count":18710019,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["augmentation","bert","chinese-nlp","eda","nlp","nlp-toolkit"],"created_at":"2024-10-10T18:07:45.967Z","updated_at":"2025-01-12T20:32:54.663Z","avatar_url":"https://github.com/thinkwee.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 介绍\n-   原仓库[eda_nlp](https://github.com/jasonwei20/eda_nlp)，原论文[EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://arxiv.org/abs/1901.11196)\n-   改成了支持中文，并且默认处理成用于BERT模型输入格式，即句子对，可见样例```/data/original.csv```\n-   用于增强数据，包含了同义词替换、随机插入、随机删除、打乱顺序，至少用在BERT+分类任务上是可行的。其他模型和任务未测试\n\n# 依赖\n-   synonyms\n-   pandas\n-   请手动安装\n\n# 输入输出样例\n-   见```./data/```\n\n# 运行\n-   ```./run_augment.sh```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthinkwee%2Feda_zh_bert","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fthinkwee%2Feda_zh_bert","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthinkwee%2Feda_zh_bert/lists"}