8000 关于输出句向量维度的问题。768->128 · Issue #58 · terrifyzhao/bert-utils · GitHub

More Web Proxy on the site http://driver.im/

关于输出句向量维度的问题。768->128 #58

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.

Sign up for GitHub

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

Jump to bottom

Open

XGodLike opened this issue Apr 5, 2020 · 3 comments

XGodLike commented

我的场景是两个文本的相似度，思路是：微调后，抽取的最后一层池化作为了句向量，用余弦来计算相似度。是768维的，效果还可以，后来因为有个需求需要降低到128维，我直接在768维后面接了一个全连接降到128维了。但是效果就不好了....是不是这种方式不可行？

fanruifeng commented

同问

Lich-King000 commented

@XGodLike 你好，请问这个问题你解决了吗？直接接全连接层可行吗？

fanruifeng commented

encoder之后,将输出层进行均值操作,在接全连接层, 你自己设计你的解码操作, 两个输入和输出,共享这个编码层,最后组件一个余弦相似度模型层,试试

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

0