Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems

Hung Le, Doyen Sahoo, Nancy Chen, Steven Hoi


Abstract
Developing Video-Grounded Dialogue Systems (VGDS), where a dialogue is conducted based on visual and audio aspects of a given video, is significantly more challenging than traditional image or text-grounded dialogue systems because (1) feature space of videos span across multiple picture frames, making it difficult to obtain semantic information; and (2) a dialogue agent must perceive and process information from different modalities (audio, video, caption, etc.) to obtain a comprehensive understanding. Most existing work is based on RNNs and sequence-to-sequence architectures, which are not very effective for capturing complex long-term dependencies (like in videos). To overcome this, we propose Multimodal Transformer Networks (MTN) to encode videos and incorporate information from different modalities. We also propose query-aware attention through an auto-encoder to extract query-aware features from non-text modalities. We develop a training procedure to simulate token-level decoding to improve the quality of generated responses during inference. We get state of the art performance on Dialogue System Technology Challenge 7 (DSTC7). Our model also generalizes to another multimodal visual-grounded dialogue task, and obtains promising performance.
Anthology ID:
P19-1564
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5612–5623
Language:
URL:
https://aclanthology.org/P19-1564
DOI:
10.18653/v1/P19-1564
Bibkey:
Cite (ACL):
Hung Le, Doyen Sahoo, Nancy Chen, and Steven Hoi. 2019. Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5612–5623, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems (Le et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1564.pdf
Video:
 https://aclanthology.org/P19-1564.mp4
Code
 henryhungle/MTN
Data
SIMMC2.0