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

Add Dialogue Policy #156

Open
kbalog opened this issue Nov 21, 2022 · 2 comments · May be fixed by #238
Open

Add Dialogue Policy #156

kbalog opened this issue Nov 21, 2022 · 2 comments · May be fixed by #238
Assignees
Labels
improvement Improvement P1 Medium priority
Milestone

Comments

@kbalog
Copy link
Contributor

kbalog commented Nov 21, 2022

next_intent() goes here

@kbalog kbalog added improvement Improvement P2 Low priority labels Nov 21, 2022
@NoB0 NoB0 removed their assignment Mar 17, 2023
@NoB0 NoB0 added P1 Medium priority and removed P2 Low priority labels Mar 17, 2023
@WerLaj
Copy link
Collaborator

WerLaj commented May 5, 2023

@NoB0 @kbalog We could have a separate class DialoguePolicy that implements the next_dialogue_act() method that predicts the next dialogue act given the last user utterance and dialogue_history. This method is used in receive_utterance() in the agent to generate the agent's response. We probably want to predict the next dialogue act not only the intent, as intent annotations may be needed for generating the agent's response.

@WerLaj WerLaj self-assigned this May 5, 2023
@kbalog
Copy link
Contributor Author

kbalog commented May 27, 2023

@WerLaj Yes to creating a new DialoguePolicyclass. I suppose in most cases we'd want to predict next dialogue act, but that'll likely involve next intent prediction as a first substep.

@NoB0 NoB0 added this to the v1.0.0 milestone Jul 3, 2023
@WerLaj WerLaj linked a pull request Aug 2, 2023 that will close this issue
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
improvement Improvement P1 Medium priority
Projects
None yet
Development

Successfully merging a pull request may close this issue.

3 participants