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

English Phrase FST assumes definitions in itwewina format (not language agnostic) #1209

Open
fbanados opened this issue Jan 11, 2025 · 0 comments

Comments

@fbanados
Copy link
Member

Looks like the english phrase FSTs make strong assumptions about the sentence structure for translation, based on itwewina. This means things like 3s as the standard form in the definition, which is not the case e.g. in WordNet definitions which take the infinitive.

For a search, say, of "I ate", eventually we would have an appropriate analysis to inflect over the definition. In wordnet, we have "take in solid food". Because it's not 3s, the inflection does not change the phrase. If the definition were instead "s/he takes in solid food", then we could inflect it in the results. However, we currently can't (only because of the FST, I've written the code although it needs more testing)

In general the definition structure for the english side should be more flexible, with some way to specify in the system the structure of the definitions or at least accept infinitive-based definitions which seem pretty common in our currently supported target language.

@fbanados fbanados changed the title English Phrase FST assumes definitions in CW-format English Phrase FST assumes definitions in itwewina format (not language agnostic) Jan 11, 2025
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