f1 score became 0

[huge-melon]

Why f1 score falls to zero when I'm training the model. Do you have some idea?

[ThanhDucPham]

Hi, I have encountered with this problem, I think we have some reasons:

• Our model need more epoch to learn about these label difference to "O" label. Then, let's try more epoch.
• In this repos, I use Adadelta optimizer according to the original paper, but as I know, Adadelta converge very slow, so try Adam optimizer. It work for me with this repos: https://github.com/ThanhDucPham/Event-Detection-and-Domain-Adaptation-with-Convolutional-Neural-Networks/blob/master/model.py