Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

教师和学生相似度是1但老师和教师相似度小于0.9 #137

Open
2 tasks
funicia opened this issue Nov 25, 2022 · 1 comment
Open
2 tasks

教师和学生相似度是1但老师和教师相似度小于0.9 #137

funicia opened this issue Nov 25, 2022 · 1 comment
Assignees
Labels

Comments

@funicia
Copy link

funicia commented Nov 25, 2022

现在行为

synonyms.compare('教育机构学生', '教育机构教师')
结果是1.0 ,这两个字符串相似度应该低于0更合理些。

synonyms.compare('学生', '教师')
这个结果也是1.0

synonyms.compare('学生', '老师')
这个结果是0.896

synonyms.compare('教师', '老师')
这个结果是0.898

操作系统

  • Windows
  • Linux(Debian, CentOS, Ubuntu, etc.)

解决方案

代码版本

Open Source for the World

banner

@hailiang-wang
Copy link
Member

hailiang-wang commented Nov 25, 2022

I can not fix this badcase at the moment.

Thanks for your feedback, the badcases can not be fixed with a big corpus, as it is done in machine learning way.
The model pretrained in Synonyms uses public corpus four years ago, so, the open data for training should be available.

To learn more about how Synonyms works, please read this book.
https://github.com/l11x0m7/book-of-qna-code

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

2 participants