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

有尝试过其他相关性的编码吗? #27

Open
JerryNeVerMORE opened this issue Nov 14, 2024 · 1 comment
Open

有尝试过其他相关性的编码吗? #27

JerryNeVerMORE opened this issue Nov 14, 2024 · 1 comment
Labels
question Further information is requested

Comments

@JerryNeVerMORE
Copy link

Question

作者你好,我尝试使用了relation的编码加入到self-attention,在训练早期效果确实很好。请问你们有尝试过其他不同的关系编码吗?感觉像论文中一样描述相对位置偏移的方法和思路应该有不少

补充信息

No response

@JerryNeVerMORE JerryNeVerMORE added the question Further information is requested label Nov 14, 2024
@xiuqhou
Copy link
Owner

xiuqhou commented Nov 17, 2024

除了位置关系,我还尝试过编码类别关系,用交叉熵描述类别见的相对距离,但没有看到明显的精度提升。我推测是类别关系比较偏向语义,可能引入语言模型来构建类别关系会有效果。

其他还有基于统计的关系,比如预先统计两个类别在数据集中同时出现的概率。但就没尝试过了。

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

No branches or pull requests

2 participants