search

thunlp / NRE

Neural Relation Extraction, including CNN, PCNN, CNN+ATT, PCNN+ATT
MIT License
810 stars 309 forks source link

Can't get the same PR curve as in the paper #8

Closed ppuliu closed 7 years ago

ppuliu commented 7 years ago

Hi,

Thanks for the great work. I'm trying to reproduce the results but having some trouble.

First, I just used the "pr.txt" file in the "NRE/PCNN+ATT/out/" directory and plotted the PR curve. Then, I re-ran the test part of the program (without retraining) and plotted the PR curve with the newly generated "pr.txt" file.

What I plotted: image

Somehow, they are different and also not the same as figure 3 in the paper. Could you please elaborate on the possible reasons? Thanks.

ppuliu commented 7 years ago

Closing this issue as the author has responded this question in another issue: https://github.com/thunlp/NRE/issues/5