This repository has been archived by the owner on Dec 16, 2022. It is now read-only.
Minor WTQ ERM model and dataset reader fixes for demo #3068
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Outdated suggestions cannot be applied.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.
Earlier we used the final states from the ERM trainer both for training and prediction, but that meant that we could not use interactive beam search on an ERM trained model. The main change in this PR is to use beam search in the ERM model while testing. I confirmed that the dev accuracy of a trained model remains the same after this change.