Open marksverdhei opened 3 years ago
Turned out that the naive bayes model is still better than the rnn. This is unacceptable, and therefore we must tune hyperparameters and experiment so that it can outperform the baseline
Some approaches to upgrade or replace our current neural model:
Or simple replace the rnn with a classification layer on the contextual models. Apart from that, tune hyperparams using the new conf setup
Turned out that the naive bayes model is still better than the rnn. This is unacceptable, and therefore we must tune hyperparameters and experiment so that it can outperform the baseline