GH-512: Minor embedding fixes #520
Merged
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Outdated suggestions cannot be applied.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.
This PR fixes a few minor issues in preparation for 0.4.1 release.
DocumentLSTMEmbeddingsare marked as deprecated but not removed so that serialized models still work. The deprecation warning points to the newDocumentRNNEmbeddingsclass as class to be used instead.BytePairEmbeddingsthrew an error for empty words. Now, a null vector is used for empty words instead.the
load_text_classification_corpus()methods of theNLPTaskDataFetcherpreviously tokenized all corpora by default. But some text classification corpora, such as TREC_6 are already tokenized. So we added an option to turn tokenization off.added Turian embeddings which are very small and will hopefully speed up integration tests. Load with
WordEmbeddings('turian')