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

Tune Kim CNN for SST-2 and Improve SST-1 Results with Dataset/Initialization Changes #133

Merged
merged 3 commits into from
Jul 12, 2018
Merged

Tune Kim CNN for SST-2 and Improve SST-1 Results with Dataset/Initialization Changes #133

merged 3 commits into from
Jul 12, 2018

Conversation

tuzhucheng
Copy link
Member

  • Update Kim CNN Dataset to use default min_freq=1 and use Uniform[-0.25, 0.25] distribution for unknown tokens (following original implementation by Yoon Kim)
  • Tune results for SST-2
  • Re-tune SST-1
Test Accuracy on SST-1 rand static non-static multichannel
Paper 45.0 45.5 48.0 47.4
PyTorch using above configs 44.3 47.9 48.6 49.2
Test Accuracy on SST-2 rand static non-static multichannel
Paper 82.7 86.8 87.2 88.1
PyTorch using above configs 83.0 86.4 87.3 87.4

@tuzhucheng tuzhucheng requested a review from Impavidity July 11, 2018 01:49
@tuzhucheng
Copy link
Member Author

Thanks to @EmilyKeer for some help tuning SST-2.

Related to #58

Impavidity
Impavidity approved these changes Jul 12, 2018
View reviewed changes
Copy link
Member

@Impavidity Impavidity left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Great job ! LGTM.

@tuzhucheng tuzhucheng merged commit 82bf90f into castorini:master Jul 12, 2018
@tuzhucheng tuzhucheng deleted the kim-cnn-sst-2 branch July 12, 2018 02:08
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@Impavidity Impavidity

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

None yet
2 participants
@tuzhucheng @Impavidity