Add weight mask that are applied to scores during retrieval #50
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
xhluca
changed the title
|
@dl423 FYI |
|
@xhluca Thank you! Really appreciate that you implemented this feature, sorry I didn't get around to implementing this. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR should close #35, as the new weight_mask allows the use of binary masks (see new tests) as well as any floating point mask, making it a general purpose weighting mechanism for post-scoring but before top-k candidate selection. At the moment only a single mask (of shape
(D,)for D documents) is accepted, mainly due to infeasibility of having a(Q,D)mask when D is large. Future PRs can add support for 2-D masks.