search

hy-struggle / PRGC

PRGC: Potential Relation and Global Correspondence Based Joint Relational Triple Extraction
107 stars 16 forks source link

The result of the experiment did not come up to expectations . Why ? #8

Open chensongcan opened 2 years ago

chensongcan commented 2 years ago

When batch size =30, other parameters are the same as yours, F1 score is only 90.5 in NYT-star test datasets. It does not reach the 92.6 mentioned in the paper.

chensongcan commented 2 years ago

Were the published results achieved using the bert-base or bert-large model?

hy-struggle commented 2 years ago

Were the published results achieved using the bert-base or bert-large model?

look at the appendix

chensongcan commented 2 years ago

ok, thanks for your reply. Please reply the first problem, when train 50 epochs, the F1 score is still only achieved 90.5

Wangrulin-1128 commented 10 months ago

use my dataset the f1 only reach 30%,what can i do to improve the f1?