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

Enhanced Rule-Based Inference State #96

Open
josephbirkner opened this issue May 27, 2019 · 3 comments
Open

Enhanced Rule-Based Inference State #96

josephbirkner opened this issue May 27, 2019 · 3 comments
Assignees
@Waguramu @emlozin @l-laura
Labels
inference 💡 roboy 🤖 This issue is related to ravestate's Roboy personality set.
Milestone
Inference

Comments

@josephbirkner
Copy link
Collaborator

josephbirkner commented May 27, 2019 •
edited
Loading

Try to come up with an rule-based inference state implementation, that does...

  • ... recognize predicates
  • ... recognize subject (interlocutor vs roboy vs 3rdparty)
  • ... recognize object answer and
    • ... write it to memory if it's a statement!
    • ... determine truth if it's a question!

Please put this state into a new ravestate_inference module. ravestate_inference could offer prop_predicate and prop_subject which would be written by the ravestate_persqa smalltalk state.
@josephbirkner josephbirkner added this to the Inference milestone May 27, 2019
@josephbirkner josephbirkner changed the title Less stupid Inference state Enhanced Rule-Based Inference State May 27, 2019
@josephbirkner josephbirkner added inference 💡 roboy 🤖 This issue is related to ravestate's Roboy personality set. labels May 28, 2019
@josephbirkner
Copy link
Collaborator Author

Let's create a decision tree! 🎄

@josephbirkner josephbirkner assigned l-laura, Waguramu and emlozin and unassigned Toseban Jun 17, 2019
@josephbirkner josephbirkner mentioned this issue Jun 28, 2019
Open
@josephbirkner
Copy link
Collaborator Author

Depends on #112

@josephbirkner
Copy link
Collaborator Author

josephbirkner commented Aug 8, 2019 •
edited
Loading

Conclusions from Datasheet (https://docs.google.com/spreadsheets/d/18i_0Izgyz2pwxN_d-GDHrE0pN_pdpYvRVCAGgPEKn7o/edit#gid=0):

  • We need to annotate triple elements / named entities in the samples
  • We need robust Named Entity Recognition
  • Which features to use?
    • Is Yes/No Question?
    • Is W Question
    • Has Named Entity (ORG/LOC/PER/....)
    • Has I/you/...
    • ...
  • If we do a decision-tree, what does it use as labels?
    • does it decide (subj, pred, senttype) triples
    • or do we have three trees?

@josephbirkner josephbirkner mentioned this issue Aug 8, 2019
Closed
10 tasks
@josephbirkner josephbirkner mentioned this issue Sep 15, 2019
Merged
11 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@Waguramu Waguramu

@emlozin emlozin

@l-laura l-laura

Labels
inference 💡 roboy 🤖 This issue is related to ravestate's Roboy personality set.
Projects
None yet
Milestone
Inference
Development

No branches or pull requests
5 participants
@Toseban @Waguramu @josephbirkner @emlozin @l-laura