Giters

malllabiisc / RESIDE

EMNLP 2018: RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

question about how to get the performance in your paper?

YaNjIeE opened this issue · comments

commented

Hi, @svjan5
Sorry to bother you, but when I download your code and run it like you said in readme file:
E%S(Z$YTGI69(`HI0CW~I}8
I didn't change any parameter or hyper-parameter， but I got result auc: 0.39, it didn't match your paper auc: 0.416 on Riedel.
G9%CXMDTWZ~GAL00YJVHR(3
So, I wonder if you can tell me how to match the performance reported in the paper? If I need to change some settings for matching the auc and PR-curves that your paper showed?
Thank you very much.

commented

Hi @yanjieg,
I would recommend to check the results with different parameter initializations (seed). I will also check once whether I missed something while cleaning the code.