Made off-by-one adjustments for specials tokens #41
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
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Outdated suggestions cannot be applied.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.
preprocess.tokenize()pads texts with -2 (the SKIP index), which puts it in the corpus vocabulary andcounts_loose._loose_keys_ordered()then prepends the specials tokens (OOV and SKIP) while makingkeys_loose, thus allocating two array entries to SKIP (instead of 1 as desired, I assume).This becomes a problem when you try to train a model using all of the words in the vocabulary, and in lda2vec_run.py,
model.sampler.W.data[:, :] = vectors[:n_vocab, :]W is created with one more row than there are unique words + specials, since
n_keysis derived from the concatenated array length created in_loose_keys_ordered(), and not the unique number of words in the vocabulary as created bycounts_loose