Fix error on large documents #4
Open
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
Running QAnom on a large document results in an error because the entire document is attempted to be processed at once: ``` RuntimeError: The expanded size of the tensor (12646) must match the existing size (512) at non-singleton dimension 1. Target sizes: [1, 12646]. Tensor sizes: [1, 512] ``` A workaround is to use a separate pipeline without QAnom to first split the document into sentences (assuming that your sentences are <512 tokens), but that is cumbersome. Instead do what NominalizationDetector already does: give a list of sentences to the tokenizer. Now the limit is 512 tokens in a sentence, which is a much more reasonable limit. Signed-off-by: Edwin Török <[email protected]>
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Outdated suggestions cannot be applied.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.
Running QAnom on a large document results in an error because the entire document is attempted to be processed at once:
A workaround is to use a separate pipeline without QAnom to first split the document into sentences (assuming that your sentences are <512 tokens), but that is cumbersome.
Instead do what NominalizationDetector already does: give a list of sentences to the tokenizer.
Now the limit is 512 tokens in a sentence, which is a much more reasonable limit.