This repository has been archived by the owner on Nov 22, 2022. It is now read-only.
Vocab Limited Pretrained Embedding [2/5] #1248
Closed
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
Summary: In local bento experiments, often nearest neighbors / items nearby in the embedding space tended to be misspellings of the original word. This isn't really useful for spoken language since there won't be many misspellings, so instead this diff adds a subclass of `PretrainedEmbeddings` that restricts the embedding space to only contain known vocab words. From local experiments, the results here seem much more consistent with what is expected from kNN in the embedding space. Reviewed By: geof90 Differential Revision: D19818803 fbshipit-source-id: bfac18887990f7a816e30000f8fbbfad37788fd3
facebook-github-bot
added
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D19818803 |
|
This pull request has been merged in f907783. |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
Summary: In local bento experiments, often nearest neighbors / items nearby in the embedding space tended to be misspellings of the original word. This isn't really useful for spoken language since there won't be many misspellings, so instead this diff adds a subclass of
PretrainedEmbeddingsthat restricts the embedding space to only contain known vocab words. From local experiments, the results here seem much more consistent with what is expected from kNN in the embedding space.Reviewed By: geof90
Differential Revision: D19818803