Increase HotPotQA lookup range to a full paragraph #96
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
dosubot
bot
added
the
size:XS
There was a problem hiding this comment.
@Ryan-Rhys is it important that we split on sentences instead of paragraphs? The period-based splitting was getting tripped up on things like "U.S." (which would hit the two-sentence window)
sidnarayanan
approved these changes
Oct 27, 2024
jamesbraza
approved these changes
Oct 27, 2024
|
Bonus points for unit test |
|
closing as this change is also included in #99 |
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Outdated suggestions cannot be applied.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.
Currently, the behavior is to return the two sequences before and after the lookup term. However, this can cause issues in cases like "Milhouse was named after U.S. president Richard Milhous Nixon", where the important information is not returned if action is Lookup("Milhouse"). This PR proposes returning the full paragraph instead.