elmo-bilstm-cnn-crf icon indicating copy to clipboard operation
elmo-bilstm-cnn-crf copied to clipboard

Published 20 hours ago • verified publisher icon UKPLab

Hyperparameter optimization

Open Mahmedturk opened this issue 5 years ago • 4 comments

How are you optimizing hyperparameter space in this implementation? Grid search or random search or bayesian?

Mahmedturk avatar Mar 28 '19 01:03 Mahmedturk

I would recommend random search. See: http://www.jmlr.org/papers/volume13/bergstra12a/bergstra12a.pdf

nreimers avatar Mar 28 '19 08:03 nreimers

Is it already implemented in this model? and what is the loss function of this model with CRF as a classifier?

Mahmedturk avatar Apr 01 '19 05:04 Mahmedturk

No, you would need to implement it by yourself.

For the loss function see line 51: https://github.com/UKPLab/elmo-bilstm-cnn-crf/blob/master/neuralnets/keraslayers/ChainCRF.py

nreimers avatar Apr 01 '19 08:04 nreimers

okay.

Mahmedturk avatar Apr 06 '19 10:04 Mahmedturk