GH-229: multilingual embeddings #234
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
|
👍 Great! |
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Outdated suggestions cannot be applied.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.
Closes #229
Add FastText embeddings for 30 languages (English, German, Dutch, Italian, French, Spanish, Swedish, Danish, Norwegian, Czech, Polish, Finnish, Bulgarian, Portuguese, Slovenian, Slovakian, Romanian, Serbian, Croatian, Catalan, Russian, Hindi, Arabic, Chinese, Japanese, Korean, Hebrew, Turkish, Persian, Indonesian)
Each language gets a wiki and a crawl embedding and is called using the two-letter language code. (
WordEmbeddings('de')orWordEmbeddings('de-wiki')to instantiate the wiki embedding for German andWordEmbeddings('de-crawl')to instantiate the crawl embedding)We add more LM embeddings from @stefan-it, namely the Dutch CharLM embeddings, callable with
CharLMEmbeddings('dutch-forward')andCharLMEmbeddings('dutch-backward')New multilingual character LM embeddings, computed using a very large corpus of six languages (English, German, Italian, French, Dutch and Polish) and applicable to text in any of these languages. It even works for some other languages such as Spanish. Instantiate with
CharLMEmbeddings('multi-forward')andCharLMEmbeddings('multi-backward')