bug fix: beam_threshold is in log_10 and needs to be transformed befo… #16
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
…re it's passed the the ttable.
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Outdated suggestions cannot be applied.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.
…re it's passed the the ttable.
beam_threshold is the a threshold in log space (indicated by it's default value of -4.0). It used to be directly passed like this to ExportToFile, which then internally got multiplied with max_p (a probability NOT in log space) to get the threshold. This threshold was then used to be compare to log probabilities. This led to everything being pruned if max_p < 0.3 (e.g. if max_p=0.2 then threshold=0.2*-4=-0.8 which leads to log(max_p) < threshold). Anyway, I changed this to directly pass a probability to ExportToFile, so that probabilities are compare to probabilities.