You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The reason why the tests fail in #3502 is because of an edge case.
If the input to tokenizer.batch_encode_plus() consists of a tokenized string that results in a list of exactly two strings ([[16], [.]] in issue #3502) then it is treated as a pair of input sequences (=> [CLS] input_sequence_1 [SEP] input_sequence_2 [SEP]) but this behavior should only happen if the input list consists of two untokenized strings.
Does this mean that batch_encode_plus is supposed to handle "pre-tokenized" inputs? I thought this was something introduced by #3185 with a specific flag is_pretokenized (cc @mfuntowicz)
sshleifer
changed the title
[Tokenization] fix egde gase for bert tokenization
[Tokenization] fix edge gase for bert tokenization
Mar 31, 2020
sshleifer
changed the title
[Tokenization] fix edge gase for bert tokenization
[Tokenization] fix edge case for bert tokenization
Mar 31, 2020
Does this mean that batch_encode_plus is supposed to handle "pre-tokenized" inputs? I thought this was something introduced by #3185 with a specific flag is_pretokenized (cc @mfuntowicz)
@mfuntowicz showed me the is_pretokenized flag for tokenizers v3.0.0 so this makes everything much easier
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR fixes #3502 .
The reason why the tests fail in #3502 is because of an edge case.
If the input to
tokenizer.batch_encode_plus()consists of a tokenized string that results in a list of exactly two strings ([[16], [.]]in issue #3502) then it is treated as a pair of input sequences (=> [CLS] input_sequence_1 [SEP] input_sequence_2 [SEP]) but this behavior should only happen if the input list consists of two untokenized strings.