-
Notifications
You must be signed in to change notification settings - Fork 1
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
数据集构建 #2
Comments
inverse:头尾预测,query 嵌入用simkgc,transe之类的。他论文和代码里挺清楚的了 |
query嵌入是预先通过KGE方法计算出来的,比如TransE、ComplEx等,这些方法会给每个实体和关系分配嵌入向量,然后基于某种评分指标计算出query的嵌入; |
请问您有跑代码吗?跑得如何? |
请问是论文里面哪部分提了?无论是inverse的解释还是query嵌入用TransE都没看到啊。 |
是的,我在我最新的工作复现了这篇论文。正如作者所展示的,微调的llama确实可以提升pre-train model的预测精度。具体的复现难度主要是数据获取部分,我仅仅复现了SimKGC作为pre-train的DIFT版本,其他模型我认为原理是一致的。 如果您对这篇论文有所疑惑,我非常乐意为你提供帮助。邮件交流:ldp2211479@gmail.com |
感谢您的回复,我想您的帮助应该会为我带来极大的便利。 |
请问训练数据集中inverse的作用是什么。
以及query 嵌入是怎么计算的,怎么得到的query_id
The text was updated successfully, but these errors were encountered: