no code implementations • 1 Jan 2021 • Rafael Kourdis, Gabriel Gordon-Hall, Philip John Gorinski
In such settings, it becomes important to estimate the positive or negative influence auxiliary tasks will have on the target.
no code implementations • ACL 2020 • Gabriel Gordon-Hall, Philip John Gorinski, Shay B. Cohen
Deep reinforcement learning is a promising approach to training a dialog manager, but current methods struggle with the large state and action spaces of multi-domain dialog systems.
no code implementations • 17 Apr 2020 • Gabriel Gordon-Hall, Philip John Gorinski, Gerasimos Lampouras, Ignacio Iacobacci
We present our submission to the End-to-End Multi-Domain Dialog Challenge Track of the Eighth Dialog System Technology Challenge.