In this paper, we present a multimodal dialogue system for Conversational Image Editing. We formulate our multimodal dialogue system as a Partially Observed Markov Decision Process (POMDP) and trained it with Deep Q-Network (DQN) and a user simulator. Our evaluation shows that the DQN policy outperforms a rule-based baseline policy, achieving 90\% success rate under high error rates. We also conducted a real user study and analyzed real user behavior.
@article{arxiv.2002.06484,
title = {A Multimodal Dialogue System for Conversational Image Editing},
author = {Tzu-Hsiang Lin and Trung Bui and Doo Soon Kim and Jean Oh},
journal= {arXiv preprint arXiv:2002.06484},
year = {2020}
}
Comments
Accepted at 2nd Conversational AI Workshop at NeurIPS 2018