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

实验相关问题 #9

Closed
Hou-jing opened this issue May 27, 2022 · 2 comments
Closed

实验相关问题 #9

Hou-jing opened this issue May 27, 2022 · 2 comments

Comments

@Hou-jing
Copy link

(1)在根据频次优化时(Frequency Refinement),体现在代码中,是否为:
myverbalizer = KnowledgeableVerbalizer(tokenizer, classes=class_labels, candidate_frac=cutoff, pred_temp=args.pred_temp, max_token_split=args.max_token_split).from_file(f"{args.openprompt_path}/scripts/{scriptsbase}/knowledgeable_verbalizer.{scriptformat}"),其中的cutoff是否为实验中提到的阈值呢?不知道理解的对不对。
(2)在few-shot实验中,为何没有将support set的label值remove掉呢?
我看论文中提到的是“
. Our proposed Contextualized
Calibration utilizes a limited amount of unlabeled
support data to yield significantly better results”,
但是,在实验中是,却将其注释掉了,这里有些不解。
image
**

@ShengdingHu
Copy link
Collaborator

  1. 是的,cutoff是阈值
  2. 我的代码中应该没有注释掉 https://github.com/thunlp/KnowledgeablePromptTuning/blob/main/zeroshot.py#L111,可能是你不小心注释了?

@Hou-jing
Copy link
Author

谢谢,我看到了,麻烦了

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