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

How seq2seq_go_bot model was created? #281

Closed
tomferreira opened this issue Jun 20, 2018 · 2 comments
Closed

How seq2seq_go_bot model was created? #281

tomferreira opened this issue Jun 20, 2018 · 2 comments
Assignees
Labels

Comments

@tomferreira
Copy link

Hi,

This is a very promising project, but I'm having troubles in understand how the models was created, e.g. seq2seq_go_bot?

What train/test/validation data was used?
How the model was built?

Thanks!

@vikmary vikmary self-assigned this Jun 28, 2018
@vikmary
Copy link
Contributor

vikmary commented Jun 28, 2018

Hi, thanks for the feedback.

Concerning seq2seq_go_bot: the documentation is still not finished, and the model is being actively improved. (Within a month a much better model is being released.)

Train/valid/test data is used from here. It contains dialogues from three distinct domains: calendar scheduling, weather information retrieval, and point-of-interest navigation.

The model is a simplified version of model from the same Stanford guys.

Please wait till we update the details of implementation.

@tomferreira
Copy link
Author

Thanks!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

2 participants