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

sentence-bert #16

Open
LXLZH opened this issue Jun 15, 2021 · 4 comments
Open

sentence-bert #16

LXLZH opened this issue Jun 15, 2021 · 4 comments

Comments

@LXLZH
Copy link

LXLZH commented Jun 15, 2021

请问sentence-bert 用在 BEFAQ的架构图里面的那一部分?

@xiaoyichao
Copy link
Collaborator

请问sentence-bert 用在 BEFAQ的架构图里面的那一部分?

已经更新到架构题里了,主要用于向量召回和计算余弦相似度。

@xiaoyichao
Copy link
Collaborator

请问sentence-bert 用在 BEFAQ的架构图里面的那一部分?

之前我们是把doc的向量存储到二进制文件中,后来把dco的向量存储到了es 中。

@LXLZH
Copy link
Author

LXLZH commented Jun 15, 2021

请问sentence-bert 用在 BEFAQ的架构图里面的那一部分?

之前我们是把doc的向量存储到二进制文件中,后来把dco的向量存储到了es 中。
看您架构图的意思是将文本向量化,使用sentence-bert应该不用分词吧。

@xiaoyichao
Copy link
Collaborator

请问sentence-bert 用在 BEFAQ的架构图里面的那一部分?

之前我们是把doc的向量存储到二进制文件中,后来把dco的向量存储到了es 中。
看您架构图的意思是将文本向量化,使用sentence-bert应该不用分词吧。

是的。sentence-bert 不需要分词,但是jaccard等算法需要使用分词的结果。

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