feat: Add skip-gram word embeddings with nearest-neighbor demo - #7
Open
ThomasHartDev wants to merge 1 commit into
Open
feat: Add skip-gram word embeddings with nearest-neighbor demo#7ThomasHartDev wants to merge 1 commit into
ThomasHartDev wants to merge 1 commit into
Conversation
Train center/context embedding tables on a small corpus via full-softmax skip-gram, then rank neighbors by cosine similarity on the center rows.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Skip-gram embeddings trained end to end in numpy: center and context tables, full-softmax NLL, minibatch SGD, then cosine nearest neighbors on the center rows. Ships a small multi-sentence toy corpus so capital-city and animal clusters show up in the neighbor lists, plus finite-difference checks on the softmax gradient so the backprop path is not just trust-me code.