search

jiesutd / LatticeLSTM

Chinese NER using Lattice LSTM. Code for ACL 2018 paper.
1.79k stars 457 forks source link

Maybe something wrong, the training spent a long time ,but the performance is too low in demo data #20

Closed OYE93 closed 6 years ago

OYE93 commented 6 years ago

Hi Jie, thank for your works on Chinese NER, I downloaded the code and embedding files, and run the demo, however the training spent a long time, the performance is not good, f-value is adout 0.4 after 50 epoch. But I didn't know where I did wrong. Environment: python2.7, pytorch0.3.0, gpu1080 Thanks!

jiesutd commented 6 years ago

Hi , the demo only use a very limited data. It is only used for demo. So it is reasonable that the performance is low. You need to change your own data to train your own model.

OYE93 commented 6 years ago

Ok, thanks! I will try it on a bigger dataset.