bug fix in get_sentiment function #206
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
tejasvaidhyadev
changed the title
|
@aviks |
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Outdated suggestions cannot be applied.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.
As mentioned #205 and #187
Bug fixed in sentiment function
In file sentiment_weights we are having having 32×5000 matrices with index-1 is default pad token embedding
But here
in src/sentiment.jl
if ele in keys(rwi) && rwi[ele] <= ( size(weight[:embedding_1]["embedding_1"]["embeddings:0"])[2] ) # there are only 5000 unique embeddings-we are allowing 5000 unique embedding excluding padding which implies 5001 unique embedding but we have only 32×5000 weight.
I am not sure about training process may be we are training on only first 5000 element with padding token then replacing above line will work.