A Multimodal Dialogue System for Conversational Image Editing - Robotics Institute Carnegie Mellon University

A Multimodal Dialogue System for Conversational Image Editing

T.-H. Lin, T. Bui, D. S. Kim, and J. Oh
Workshop Paper, NeurIPS '18 2nd Workshop on Conversational AI, November, 2018

Abstract

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.

BibTeX

@workshop{Lin-2018-113122,
author = {T.-H. Lin and T. Bui and D. S. Kim and J. Oh},
title = {A Multimodal Dialogue System for Conversational Image Editing},
booktitle = {Proceedings of NeurIPS '18 2nd Workshop on Conversational AI},
year = {2018},
month = {November},
}