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

Doubt on propagation of conjuncts in Enhanced Dependencies #561

Closed
GPPassos opened this issue Jul 25, 2018 · 4 comments
Closed

Doubt on propagation of conjuncts in Enhanced Dependencies #561

GPPassos opened this issue Jul 25, 2018 · 4 comments

Comments

@GPPassos
Copy link

The documentation of enhanced dependencies presents 3 cases: conjoined verbs and verb phrases, conjoined subjects and objects, and conjoined modifiers.

Does it mean that only these 3 cases are allowed (so, for instance, it would be forbidden to propagate an amod to two conjoined nominals in "young boys and girls", or the dependency relation in conjoined function words) or are these 3 cases merely examples?

@dan-zeman
Copy link
Member

We do not have examples with all parts of speech but coordination can apply to all parts of speech, and so does propagation of conjuncts.

@GPPassos
Copy link
Author

Thanks! May I submit a PR making this explicit?

@dan-zeman
Copy link
Member

Yes, please do.

@msklvsk
Copy link
Member

msklvsk commented Jul 28, 2018

By the way, conjoined modifiers are the most tedious part to implement enhanced dependencies for. If conjuncts are heterogeneous (e.g. adjectives mixed with noun phrases and/or clauses), you have to predict their relation, and there are dozens of combinations. Maybe it’s also worth to mention explicitly in the docs (that you have to predict).

@dan-zeman dan-zeman modified the milestones: v2.3, v2.4 Nov 13, 2018
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

3 participants