Remove sentence-end from search tree and handle its scoring in the search algorithms#183
Open
larissakl wants to merge 2 commits intomultiple_label_scorersfrom
Open
Remove sentence-end from search tree and handle its scoring in the search algorithms#183larissakl wants to merge 2 commits intomultiple_label_scorersfrom
larissakl wants to merge 2 commits intomultiple_label_scorersfrom
Conversation
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The sentence-end symbol is removed from the search tree again. In the timesync-searches, all involved label scorers score sentence-end at the end of a sequence in
finalizeHypotheses(), which is then added to the overall hypothesis score. In the tree search, this is only done for hypotheses that are in a final state of the search tree (currently all root nodes). In this case, the word-level LM score for the sentence-end token is also included.Even though it is no longer necessary, I kept the logic that handles two consecutive exits in the tree search. I think it won't have any negative effects and could maybe be useful in the future, but if you prefer, I would also agree with removing it.
Depends on #172.