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

when type not provided #1

Open
6 tasks
lopezjuanma96 opened this issue Oct 14, 2022 · 0 comments
Open
6 tasks

when type not provided #1

lopezjuanma96 opened this issue Oct 14, 2022 · 0 comments

Comments

@lopezjuanma96
Copy link
Contributor

When working with the app some pictos have undefined or miscellaneous wordtype, and also if we plan to implement this NLG somewhere else we might get sentences where no word has a wordtype assigned.

Objectives:

  • add method to assume best wordtype for words with no type provided. This differs from the one below because if other words have wordtypes we might infer them from that context.
  • add method to assume most probable wordtype if ALL sentence has no wordtype. We could assign a definite type to those word that only have one possible type, and then use the method designed for the objective above to infer the ones that have many.

Steps:

  • Create or find a source for wordtypes
  • Add a method that only assigns the most probable wordtype to each word
  • Find and implement a way to infer when words have many wordtypes
  • Join all in one process that fist goes through definitive types and then tries to infer the ones with more than one possibility, if it can't just assign the most probable.
@lopezjuanma96 lopezjuanma96 mentioned this issue Oct 14, 2022
2 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant