{"id":13595211,"url":"https://github.com/bojone/BERT-whitening","last_synced_at":"2025-04-09T10:33:03.550Z","repository":{"id":38371079,"uuid":"328531648","full_name":"bojone/BERT-whitening","owner":"bojone","description":"简单的向量白化改善句向量质量","archived":false,"fork":false,"pushed_at":"2021-06-17T03:40:26.000Z","size":87,"stargazers_count":484,"open_issues_count":6,"forks_count":66,"subscribers_count":5,"default_branch":"main","last_synced_at":"2025-04-06T02:12:41.994Z","etag":null,"topics":[],"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/bojone.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}},"created_at":"2021-01-11T02:51:18.000Z","updated_at":"2025-02-25T15:43:36.000Z","dependencies_parsed_at":"2022-08-25T06:00:51.874Z","dependency_job_id":null,"html_url":"https://github.com/bojone/BERT-whitening","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/bojone%2FBERT-whitening","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bojone%2FBERT-whitening/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bojone%2FBERT-whitening/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bojone%2FBERT-whitening/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bojone","download_url":"https://codeload.github.com/bojone/BERT-whitening/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248020593,"owners_count":21034459,"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":[],"created_at":"2024-08-01T16:01:45.753Z","updated_at":"2025-04-09T10:33:03.525Z","avatar_url":"https://github.com/bojone.png","language":"Python","funding_links":[],"categories":["BERT优化","Python"],"sub_categories":["大语言对话模型及数据"],"readme":"# BERT-whitening\n通过简单的向量白化来改善句向量质量，可以媲美甚至超过BERT-flow的效果。\n\n## 介绍\n- 博客：https://kexue.fm/archives/8321\n- 博客：https://kexue.fm/archives/8069\n- 论文：[《Whitening Sentence Representations for Better Semantics and Faster Retrieval》](https://arxiv.org/abs/2103.15316)\n\n## 使用\n\n- [eng](https://github.com/bojone/BERT-whitening/tree/main/eng): BERT-whitening在常见英文数据集上的测试；\n- [chn](https://github.com/bojone/BERT-whitening/tree/main/chn): BERT-whitening在常见中文数据集上的测试；\n- [demo.py](https://github.com/bojone/BERT-whitening/blob/main/demo.py): 早期的简单Demo。\n\n测试环境：tensorflow 1.14 + keras 2.3.1 + bert4keras 0.10.5，如果在其他环境组合下报错，请根据错误信息自行调整代码。\n\n## 下载\n\n文件合集：链接: https://pan.baidu.com/s/1qv7HuYN3bNvEzPrlnlJqEQ 提取码: vbc3\n\n## 引用\n```\n@article{su2021whitening,\n  title={Whitening Sentence Representations for Better Semantics and Faster Retrieval},\n  author={Su, Jianlin and Cao, Jiarun and Liu, Weijie and Ou, Yangyiwen},\n  journal={arXiv preprint arXiv:2103.15316},\n  year={2021}\n}\n```\n\n## 其他\n\nPyTorch版：https://github.com/autoliuweijie/BERT-whitening-pytorch\n\n## 交流\nQQ交流群：808623966，微信群请加机器人微信号spaces_ac_cn\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbojone%2FBERT-whitening","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbojone%2FBERT-whitening","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbojone%2FBERT-whitening/lists"}