You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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
The text was updated successfully, but these errors were encountered:
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
The text was updated successfully, but these errors were encountered: