Closed zseder closed 9 years ago
viterbi is done by theano, but it would be easier to run theano-independent tagging+viterbi+f1 computing with simply numpy, and add its result somehow to monitor, we don't need this information during training step
there is an f1 score computing for sequential tagging in the repo
done in #23
viterbi is done by theano, but it would be easier to run theano-independent tagging+viterbi+f1 computing with simply numpy, and add its result somehow to monitor, we don't need this information during training step