Change UNK for token-ralated processor to 1#822
Merged
jhnwu3 merged 2 commits intosunlabuiuc:masterfrom Feb 6, 2026
Merged
Conversation
jhnwu3
approved these changes
Feb 6, 2026
Collaborator
jhnwu3
left a comment
jhnwu3
left a comment
There was a problem hiding this comment.
lgtm. Thanks for looking ahead.
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Enforce a processor convention such that for token-related processors, we set PAD=0 and UNK=1 for the following reasons
lots of the interpret methods expect a natural baseline, but right now UNK= len(tokens.size), which is hard to find, and some methods (e.g. lime) use 1 as the baseline, which is incorrect (because 1 is a real feature)
for feature addition & removal in the processors, UNK token does not move around when we expand or shrink number of tokens. UNK moving around may hurt performances when we want to continous learning and changing token position.