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

Differences between “scoringmodel_rank_pool_sentfaceted” and "caching_scoringmodel_rank_pool_sentfaceted" #2

Open
JacobYuan7 opened this issue Sep 19, 2022 · 1 comment

Comments

@JacobYuan7
Copy link

JacobYuan7 commented Sep 19, 2022

Many thanks for the great work.

I find the definition of the above-mentioned functions in pp_gen_nearest.py unclear since they have even the same comments.
i) Would you mind explain a bit about the differences between these two functions?
ii) The function starting with "caching_" is used when the model is "miswordpolyenc". Would you mind explaining a bit about this model? I could not find any related details concerning this model.

I am looking forward to your reply. I'd appreciate your kind explainations. @MSheshera

@MSheshera
Copy link
Contributor

I find the definition of the above-mentioned functions in pp_gen_nearest.py unclear since they have even the same comments.

These comments are somewhat imperfect - they weren't updated as the functions were updated.

caching_ generally means that the documents are embedded and cached before the scores for ranking are computed with the model. miswordpolyenc is a model we used in early experiments during this paper but it isn't included in any experiments we reported in the paper. This model implements a model similar to, but it is not exactly alike: https://openreview.net/forum?id=SkxgnnNFvH

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