Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Wrong average embedding during inference due to a small bug in neuracoref.pyx #336

Open
valedica opened this issue Mar 11, 2022 · 0 comments · May be fixed by #337
Open

Wrong average embedding during inference due to a small bug in neuracoref.pyx #336

valedica opened this issue Mar 11, 2022 · 0 comments · May be fixed by #337

Comments

@valedica
Copy link

valedica commented Mar 11, 2022 •
edited

The average embeddings can be wrongly calculated during inference due to a small bug in neuralcoref.pyx:

neuralcoref/neuralcoref/neuralcoref.pyx

Line 896 in 60338df

if token.lower not in PUNCTS:

PUNCTS is a list of strings, while token.lower is an integer hash.
This means that punctuation embeddings will be added to the average embeddings of spans, causing a potential mismatch between training and inference features.
@valedica valedica linked a pull request Mar 11, 2022 that will close this issue
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Fix punctuation in average embedding valedica/neuralcoref-bert
1 participant
@valedica