{"id":33150219,"url":"https://github.com/crownpku/Small-Chinese-Corpus","last_synced_at":"2025-11-16T07:00:52.892Z","repository":{"id":50317605,"uuid":"66624413","full_name":"crownpku/Small-Chinese-Corpus","owner":"crownpku","description":"Some useful Chinese corpus datasets 中文语料小数据","archived":false,"fork":false,"pushed_at":"2020-03-29T08:43:35.000Z","size":96839,"stargazers_count":535,"open_issues_count":2,"forks_count":165,"subscribers_count":31,"default_branch":"master","last_synced_at":"2025-07-20T07:33:00.391Z","etag":null,"topics":["chinese-nlp","corpus"],"latest_commit_sha":null,"homepage":"","language":null,"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/crownpku.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null},"funding":{"github":"crownpku","patreon":null,"open_collective":null,"ko_fi":null,"tidelift":null,"community_bridge":null,"liberapay":null,"issuehunt":null,"otechie":null,"custom":null}},"created_at":"2016-08-26T06:57:40.000Z","updated_at":"2025-06-26T08:25:23.000Z","dependencies_parsed_at":"2022-09-06T13:11:38.891Z","dependency_job_id":null,"html_url":"https://github.com/crownpku/Small-Chinese-Corpus","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/crownpku/Small-Chinese-Corpus","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/crownpku%2FSmall-Chinese-Corpus","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/crownpku%2FSmall-Chinese-Corpus/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/crownpku%2FSmall-Chinese-Corpus/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/crownpku%2FSmall-Chinese-Corpus/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/crownpku","download_url":"https://codeload.github.com/crownpku/Small-Chinese-Corpus/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/crownpku%2FSmall-Chinese-Corpus/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":284672648,"owners_count":27044736,"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","status":"online","status_checked_at":"2025-11-16T02:00:05.974Z","response_time":65,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["chinese-nlp","corpus"],"created_at":"2025-11-15T18:00:21.545Z","updated_at":"2025-11-16T07:00:52.888Z","avatar_url":"https://github.com/crownpku.png","language":null,"funding_links":["https://github.com/sponsors/crownpku"],"categories":["Contents 列表","Table of Contents","Corpus 中文语料"],"sub_categories":["综合内容","Multi-Modal Representation \u0026 Retrieval 多模态表征与检索"],"readme":"\n# 中文语料小数据：Some useful Chinese corpus datasets\n\n* 中国省市经纬度坐标：city_location/\n\n* 中国省市邮政编码大全：postal_provinces/\n\n* 全国区划和城乡划分代码(2015)：china_geo_code/\n\n* 成语大全：chengyu/\n\n* 中文人名大全及金庸小说、三国演义及红楼梦人物姓名：chi_names/\n\n* 中文命名实体识别数据sample：NER_chi/\n\n* 中文关系识别数据sample：relation_multiple_chi/\n\n* 中文阅读理解数据sample：reading_comprehension_chi/\n\n* 中文图文问答数据（基于MSCOCO）：Chinese_Visual_QA_pairs/\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcrownpku%2FSmall-Chinese-Corpus","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcrownpku%2FSmall-Chinese-Corpus","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcrownpku%2FSmall-Chinese-Corpus/lists"}