[ML] fix NLP question_answering task when best answer is only one token #88347
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
|
Pinging @elastic/ml-core (Team:ML) |
|
Hi @benwtrent, I've created a changelog YAML for you. |
|
@elasticmachine update branch |
droberts195
reviewed
Jul 8, 2022
| @@ -212,7 +212,7 @@ static void topScores( | |||
| if (startNormalized[i] == 0) { | |||
| continue; | |||
| } | |||
| for (int j = i + 1; j < (maxAnswerLength + i) && j < tokenSize; j++) { | |||
| for (int j = i; j < (maxAnswerLength + i) && j < tokenSize; j++) { | |||
There was a problem hiding this comment.
Line 227 still has i + 1. Is that correct? If it is then it would be good to add a comment explaining why a different start point is used in the two places.
…sticsearch into bugfix/ml-q_and_a-nlp-task
|
@elasticmachine update branch |
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Outdated suggestions cannot be applied.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.
There are scenarios when question_answering find the best start/end token and they are the same token. An example of this is:
context: "My name is Ben and I live in London"question: "Where do I live?"The correct answer here is
Londonand its a single token. Without this fix, we will returnin Londonwith a lower probability.