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

Question regarding "without joint-modelling" in Ablation study section #1

Open
ttklm20 opened this issue Apr 9, 2021 · 0 comments
Open

Question regarding "without joint-modelling" in Ablation study section #1

ttklm20 opened this issue Apr 9, 2021 · 0 comments

Comments

@ttklm20
Copy link

ttklm20 commented Apr 9, 2021

Thanks for your paper.

I have a question regarding the without joint modelling. I am not quite understand this part, "Finally, to study the impact of joint-modelling framework, we pre-train a model with independent word-MLM and phoneme-MLM tasks A3, where each task sees the context from respective sequence only." Could you please elaborate it? "Independent" MLM means two models? or just one model, word sequences and phoneme sequences are inputed to the model parallel, instead of concating them togething?
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
1 participant
@ttklm20