{"full_name":"hankcs/HanLP","owner":"hankcs","name":"HanLP","url":"https://github.com/hankcs/HanLP","description":"中文分词 词性标注 命名实体识别 依存句法分析 成分句法分析 语义依存分析 语义角色标注 指代消解 风格转换 语义相似度 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁转换 自然语言处理","homepage":"https://hanlp.hankcs.com/","topics":[],"language":"Python","license":"Apache-2.0","avatar":"https://avatars.githubusercontent.com/u/5326890?u=4cde654cd49edc8d24b422d0099ac743914fd5db&v=4","created_at":"2014-10-09T06:36:16Z","pushed_at":"2026-11-07T02:12:30Z","metrics":{"stars":36537,"forks":10874,"watchers":1108,"issues":1435,"prs":139,"releases":62,"issues_open":null,"issues_closed":null,"prs_open":null,"prs_closed":null,"prs_merged":null,"discussions":0},"growth":{"day":{"stars":1,"forks":-2,"base_day":"2026-11-09"}},"history":{"dates":["2026-11-09","2026-11-10"],"stars":[36536,36537],"forks":[10876,10874],"watchers":[1108,1108],"issues_open":[null,null],"prs_open":[null,null]},"boards":{},"same_owner":[],"issues":[{"number":1789,"title":"指代消解的算法／模型什么时候会开源？","comments":7,"created_at":"2022-11-09T04:50:39Z"},{"number":1792,"title":"HanLP语义相似度，希望可以输出句子的embedding以便做存储，提高效率","comments":4,"created_at":"2022-11-16T01:27:01Z"},{"number":1721,"title":"amr解析部分数字出错","comments":4,"created_at":"2022-04-15T10:04:43Z"},{"number":1802,"title":"希望增加tok保存空格的选项，以便分词后还原文本","comments":2,"created_at":"2023-01-22T11:28:16Z"},{"number":1781,"title":"关于 java 版本中使用静态变量存储字典路径的问题","comments":2,"created_at":"2022-09-05T00:51:48Z"},{"number":1733,"title":"amr部分node缺失anchors信息、label错误","comments":2,"created_at":"2022-05-17T12:30:26Z"},{"number":1535,"title":"模型优化问题","comments":2,"created_at":"2020-08-17T09:33:44Z"}],"discussions":[],"latest_release":{"name":"v2.1.1 Ancient Chinese Support","tag":"v2.1.1","published_at":"2025-01-13T01:19:55Z","body":"After supporting 130 languages, HanLP has officially released an [open-source Ancient Chinese model](https://hanlp.hankcs.com/docs/api/hanlp/pretrained/mtl.html#hanlp.pretrained.mtl.KYOTO_EVAHAN_TOK_LEM_POS_UDEP_LZH). This model supports automatic word segmentation, lemmatization, part-of-speech tagging, and dependency parsing for Ancient Chinese. Thanks to multi-task learning, this single model can handle all of these tasks, as well as coarse-grained/fine-grained segmentation and UPOS/XPOS/PKU part-of-speech tagging sets.\r\n\r\n- Blog post: https://www.hankcs.com/nlp/hanlp-ancient-chinese-processing-model-released.html\r\n- Demo: https://github.com/hankcs/HanLP/blob/master/plugins/hanlp_demo/hanlp_demo/lzh/demo_mtl.py\r\n- Performance: https://hanlp.hankcs.com/docs/api/hanlp/pretrained/mtl.html#hanlp.pretrained.mtl.KYOTO_EVAHAN_TOK_LEM_POS_UDEP_LZH\r\n- Visualization:\r\n\r\n![hankcs com 2025-01-12 at 4 47 53 PM](https://github.com/user-attachments/assets/bcf7aa09-9027-4fab-a20f-0bed65343ac3)\r\n\r\n\r\n**Full Changelog**: https://github.com/hankcs/HanLP/compare/v2.1.0...v2.1.1"},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-10T09:35:25Z","history_start":"2026-09-06"}