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

P a R v krajnych pripadoch #3

Open
michnov opened this issue May 18, 2017 · 0 comments
Open

P a R v krajnych pripadoch #3

michnov opened this issue May 18, 2017 · 0 comments

Comments

@michnov
Copy link

michnov commented May 18, 2017

Ak je pocet zlatych anaforov (len(gold_coreferents)) nulovy, t.j. v dokumente sa nenachadza ziadna koreferencia pozadovaneho typu, neznamena to este, ze P=1. Logicky mi to sedi ako nahradenie matematicky nedefinovaneho pripadu ked P=0/0, ale uz nie pre P=0/x pre x>0 (system tvrdi, ze tam nejaka koreferencia je).
Podobne ak je pocet automatickych anaforov nulovy, t.j. system nenasiel ziadnu koreferenciu pozadovaneho typu, neznamena to este, ze R=0. Platit by to malo iba vtedy, ak R=0/x pre x>0, ale podla mna uz nie pre R=0/0 (v dokumente naozaj ziadna koreferencia daneho typu nie je).
V tomto pripade by ale malo zaroven platit P=0/0=1.
https://github.com/Jankus1994/Coreference/blob/master/CoNLL/conll_evaluator.py#L23-L26

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