nju-websoft / OpenEA

A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs, VLDB 2020
GNU General Public License v3.0
517 stars 80 forks source link

F1,precision and recall #26

Closed wxl1351641822 closed 2 years ago

wxl1351641822 commented 3 years ago

In entity alignment,if use greedy alignment, one entity must have one answer.So,len(prediction) = len(gold) => precision=recall? If use stable alignment,len(prediction) != len(gold) => precision != recall? Is it true?

sunzequn commented 3 years ago

Yes, it is.