-
-
Notifications
You must be signed in to change notification settings - Fork 2.1k
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.
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
Add word dropout #48
Labels
feature
A new feature
Comments
alanakbik
pushed a commit
that referenced
this issue
Aug 14, 2018
First experiments are looking promising. With a word dropout of around 0.1 (i.e. approx. every tenth word gets dropped) we get at least equal and sometimes better results than without. We even saw a new SotA number for NER, but have to confirm with more experiments. This will probably be included as feature in release 0.3 |
alanakbik
pushed a commit
that referenced
this issue
Sep 17, 2018
tabergma
added a commit
that referenced
this issue
Sep 18, 2018
GH-48: added word dropout | moved dropouts into new flair.nn module
tabergma
pushed a commit
that referenced
this issue
Sep 20, 2018
tabergma
added a commit
that referenced
this issue
Sep 20, 2018
tabergma
added a commit
that referenced
this issue
Sep 20, 2018
alanakbik
pushed a commit
that referenced
this issue
Sep 21, 2018
GH-48: Add word dropout to text classifier
tabergma
added a commit
that referenced
this issue
Sep 28, 2018
tabergma
added a commit
that referenced
this issue
Sep 28, 2018
tabergma
added a commit
that referenced
this issue
Sep 28, 2018
alanakbik
pushed a commit
that referenced
this issue
Sep 28, 2018
GH-48: Don't use Locked and Word Dropout in text classifier per default
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
In a recent guest talk at Zalando Research, @hanxiao made a strong case for using word dropout in text classification. So, let's add it to Flair and evaluate it vis-a-vis standard and locked dropout.
The text was updated successfully, but these errors were encountered: