Collaborative Reasoning on Multi-Modal Semantic Graphs for Video-Grounded Dialogue Generation

Xueliang Zhao, Yuxuan Wang, Chongyang Tao, Chenshuo Wang, Dongyan Zhao


Abstract
We study video-grounded dialogue generation, where a response is generated based on the dialogue context and the associated video. The primary challenges of this task lie in (1) the difficulty of integrating video data into pre-trained language models (PLMs) which presents obstacles to exploiting the power of large-scale pre-training; and (2) the necessity of taking into account the complementarity of various modalities throughout the reasoning process. Although having made remarkable progress in video-grounded dialogue generation, existing methods still fall short when it comes to integrating with PLMs in a way that allows information from different modalities to complement each other. To alleviate these issues, we first propose extracting pertinent information from videos and turning it into reasoning paths that are acceptable to PLMs. Additionally, we propose a multi-agent reinforcement learning method to collaboratively perform reasoning on different modalities (i.e., video and dialogue context). Empirical experiment results on two public datasets indicate that the proposed model can significantly outperform state-of-the-art models by large margins on both automatic and human evaluations.
Anthology ID:
2022.findings-emnlp.442
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5988–5998
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.442
DOI:
10.18653/v1/2022.findings-emnlp.442
Bibkey:
Cite (ACL):
Xueliang Zhao, Yuxuan Wang, Chongyang Tao, Chenshuo Wang, and Dongyan Zhao. 2022. Collaborative Reasoning on Multi-Modal Semantic Graphs for Video-Grounded Dialogue Generation. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 5988–5998, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Collaborative Reasoning on Multi-Modal Semantic Graphs for Video-Grounded Dialogue Generation (Zhao et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.442.pdf