Improving Generative Visual Dialog by Answering Diverse Questions

Vishvak Murahari, Prithvijit Chattopadhyay, Dhruv Batra, Devi Parikh, Abhishek Das


Abstract
Prior work on training generative Visual Dialog models with reinforcement learning ((Das et al., ICCV 2017) has explored a Q-Bot-A-Bot image-guessing game and shown that this ‘self-talk’ approach can lead to improved performance at the downstream dialog-conditioned image-guessing task. However, this improvement saturates and starts degrading after a few rounds of interaction, and does not lead to a better Visual Dialog model. We find that this is due in part to repeated interactions between Q-Bot and A-BOT during self-talk, which are not informative with respect to the image. To improve this, we devise a simple auxiliary objective that incentivizes Q-Bot to ask diverse questions, thus reducing repetitions and in turn enabling A-Bot to explore a larger state space during RL i.e. be exposed to more visual concepts to talk about, and varied questions to answer. We evaluate our approach via a host of automatic metrics and human studies, and demonstrate that it leads to better dialog, i.e. dialog that is more diverse (i.e. less repetitive), consistent (i.e. has fewer conflicting exchanges), fluent (i.e., more human-like), and detailed, while still being comparably image-relevant as prior work and ablations.
Anthology ID:
D19-1152
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1449–1454
URL:
https://www.aclweb.org/anthology/D19-1152
DOI:
10.18653/v1/D19-1152
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
https://www.aclweb.org/anthology/D19-1152.pdf
Attachment:
 D19-1152.Attachment.pdf