AffectON: Incorporating Affect Into Dialog Generation

no code implementations • 12 Dec 2020 • Zana Bucinca, Yucel Yemez, Engin Erzin, Metin Sezgin

For generating language in a targeted affect, our approach leverages a probabilistic language model and an affective space.

Language Modelling Response Generation +1

Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents

no code implementations • 6 Aug 2019 • Nusrah Hussain, Engin Erzin, T. Metin Sezgin, Yucel Yemez

We present here a method for training a robot for backchannel generation during a human-robot interaction within the reinforcement learning (RL) framework, with the goal of maintaining high engagement level.

Imitation Learning Q-Learning +2

Speech Driven Backchannel Generation using Deep Q-Network for Enhancing Engagement in Human-Robot Interaction

no code implementations • 5 Aug 2019 • Nusrah Hussain, Engin Erzin, T. Metin Sezgin, Yucel Yemez

Our experiments demonstrate the potential of our method to train a robot for engaging behaviors in an offline manner.

reinforcement-learning Reinforcement Learning (RL)