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

关于向量的可解释性问题 #760

Open
Gladiator566 opened this issue May 10, 2024 · 1 comment
Open

关于向量的可解释性问题 #760

Gladiator566 opened this issue May 10, 2024 · 1 comment

Comments

@Gladiator566
Copy link

您好,非常棒的工作,我一直在使用bge系列模型,但目前有一个疑问,就是是否可以得知原文本中哪些关键词片段对于最终embedding表征的贡献是最大的?是否可以引入关键词权重的信息,人工的去控制感兴趣部分的关键词片段在生成embedding向量时具有更高的权重呢?请问咱们是否有过这方面的研究或者好的参考建议,谢谢!

@staoxiao
Copy link
Collaborator

Thanks for your feedback~
Embedding models are a black box, so it‘s difficult to finely control the generation process of embedding.
One possible way to let the model pay more attention to keywords is to add the keywords to the beginning of the sentence. For example: 关键词-1 关键词-1 关键词-2 关键词-2 原始文章

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

No branches or pull requests

2 participants