Subtract a low order n-gram LM from a high order n-gram LM #24
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
danpovey
reviewed
Dec 22, 2022
| @@ -118,13 +118,33 @@ class OptimizedHistKey { | |||
|
|
|||
| } // namespace | |||
|
|
|||
| class ArpaLmCompilerImplInterface { | |||
| public: | |||
| virtual ~ArpaLmCompilerImplInterface() = default; | |||
There was a problem hiding this comment.
any chance of some short comments here explaining the interface?
the only other comment I have is, of course check it doesn't change the behavior for normal inputs.
danpovey
reviewed
Dec 22, 2022
| StateId dest; | ||
| Symbol sym = ngram.words.back(); | ||
| float weight = -ngram.logprob; | ||
| float backoff = -ngram.backoff; | ||
|
|
||
| if (low_order == nullptr) { |
There was a problem hiding this comment.
is it necessary that the lm to subtract is actually of lower order? If it would work regardless, we might as well make it as general as possible and name it accordingly.
There was a problem hiding this comment.
... if it can be done elegantly, we can consider generaly linear combinations of logprobs, not just one minus the other.
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Outdated suggestions cannot be applied.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.
TODOs