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.

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

Adding basic Seq2Seq model on top of Flair Embeddings. This is because in NMT context plays a important role. #560

Closed
53X opened this issue Feb 24, 2019 · 3 comments
Labels
wontfix This will not be worked on

Comments

@53X
Copy link

53X commented Feb 24, 2019

@alanakbik , if this issue is a go, I would love to make a PR.

@alanakbik alanakbik mentioned this issue Feb 24, 2019
5 tasks
@stefan-it
Copy link
Member

stefan-it commented Feb 25, 2019

Sounds very interesting (second "hobby" of mine is NMT) Do you plan to implement a seq-to-seq from scratch or do want to use e.g. fairseq + build a model/context ontop of it?

There's an interesting Sennrich paper, that uses several linguistic input features (https://arxiv.org/abs/1606.02892) - that would be a great start :)

@53X
Copy link
Author

53X commented Feb 26, 2019

Thanks for the heads up. I will look into this paper @stefan-it

@stale
Copy link

stale bot commented Apr 30, 2020

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

@stale stale bot added the wontfix This will not be worked on label Apr 30, 2020
@stale stale bot closed this as completed May 7, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
wontfix This will not be worked on
Projects
None yet
Development

No branches or pull requests

2 participants