nndep Classifier and Config: Prevent fine-tuning with flag. #144
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
…g the word embedding gradient update. The main purpose is for those who want to provide their own embeddings and not finetune them.
|
Looks good, thanks! |
|
Merged. |
|
This implementation has a problem actually in that it deals poorly with any word embeddings in the training data that aren't in the provided embedFile. They are initialized to random vectors and then are neither treated as -UNKNOWN- nor updated in the gradient step. I think that the more faithful solution would be to treat them as -UNKNOWN-, but that's not the intention of the code. An alternative would be to selectively update those embeddings only. What do you think? I can make the change. |
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Outdated suggestions cannot be applied.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.
Add a flag (default: true) for performing the word embedding gradient update. The main purpose is for those who want to provide their own embeddings and not fine-tune them.