Content-Length: 219718 | pFad | http://github.com/luofuli/DualRL/issues/15

FB how to tune hyper-parameters to balance between sentiment accuracy and BLEU score · Issue #15 · luofuli/DualRL · GitHub
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

how to tune hyper-parameters to balance between sentiment accuracy and BLEU score #15

Open
jind11 opened this issue Oct 2, 2019 · 3 comments
Open

how to tune hyper-parameters to balance between sentiment accuracy and BLEU score #15

jind11 opened this issue Oct 2, 2019 · 3 comments

Comments

@jind11
Copy link

jind11 commented Oct 2, 2019

hi, I tried re-running your code without changing any hyper-parameters, however, I got this result: 0-1_Test(Batch:1600) Senti:77.300 BLEU(4ref):61.125(A:55.520+B:66.730) G-score:68.738 H-score:68.267 Cost time:2.57.
Could you provide some experience about how to tune the hyper-parameters so that I can balance between the sentiment accuracy and the BLEU score? Thank you so much!
@luofuli
Copy link
Owner

luofuli commented Oct 2, 2019

You can change 0.25 to a larger value, which can cause a better sentiment accuracy and worse content presentation.

DualRL/dual_training.py

Line 275 in 2fae5bb

reward = (1+0.25) * style_reward * content_reward / (style_reward + 0.25 * content_reward)

Note: The printed logs just show the results on one test set. 0-1_Test..... is the performance of test.0 and 1-0_Test.... is the performance of test.1.

@jind11
Copy link
Author

jind11 commented Oct 3, 2019

I thought in the result log: A:55.520+B:66.730, A and B correspond to two directions: 0->1 and 1->0 and the BLEU score is the average of them, am I right?

@jind11
Copy link
Author

jind11 commented Oct 6, 2019

hi, Fuli, I have tried increasing the context reward coefficient from 0.25 to 1.0 and the highest sentiment accuracy I got is 78.7%, should I further increase this coefficient? Or I should tune other hyper-parameters to increase the sentiment accuracy to what is reported in the paper? Thank you so much!

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

No branches or pull requests
2 participants
@luofuli @jind11








ApplySandwichStrip

pFad - (p)hone/(F)rame/(a)nonymizer/(d)eclutterfier!      Saves Data!


--- a PPN by Garber Painting Akron. With Image Size Reduction included!

Fetched URL: http://github.com/luofuli/DualRL/issues/15

Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy