Year: 2,016
Journal: Conference on Empirical Methods in Natural Language Processing
Languages: English
Programming languages: C
Input data:


We introduce a joint many-task model together with a strategy for successively growing its depth to solve increasingly complex tasks. Higher layers include shortcut connections to lower-level task predictions to reflect linguistic hierarchies. We use a simple regularization term to allow for optimizing all model weights to improve one task’s loss without exhibiting catastrophic interference of the other tasks.

Sign In


Reset Password

Please enter your username or email address, you will receive a link to create a new password via email.