CE-VDG: Counterfactual Entropy-based Bias Reduction for Video-grounded Dialogue Generation

Hongcheng Liu, Pingjie Wang, Zhiyuan Zhu, Yanfeng Wang, Yu Wang


Abstract
The Video-Grounded Dialogue generation (VDG) is a challenging task requiring a comprehensive understanding of the multi-modal information to produce a pertinent response. However, VDG models may rely on dataset bias as a shortcut and fail to learn the multi-modal knowledge from both video and audio. Counterfactual reasoning is an effective method that can estimate and eliminate bias on some special aspects of classification tasks. However, conventional counterfactual reasoning cannot be applied to VDG tasks directly due to the BPE algorithm. In this paper, we reformulate the counterfactual reasoning from the information entropy perspective and extend it from the classification task to the generative task, which can effectively reduce the question-related bias in the auto-regressive generation task. We design CE-VDG to demonstrate the effectiveness in bias elimination of the reformulated counterfactual reasoning by using the proposed counterfactual entropy as an external loss. Extensive experiment results on two popular VDG datasets show the superiority of CE-VDG over the existing baseline method, demonstrating the effective debiasing capability in our model considering counterfactual entropy.
Anthology ID:
2024.lrec-main.264
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
2958–2968
Language:
URL:
https://aclanthology.org/2024.lrec-main.264
DOI:
Bibkey:
Cite (ACL):
Hongcheng Liu, Pingjie Wang, Zhiyuan Zhu, Yanfeng Wang, and Yu Wang. 2024. CE-VDG: Counterfactual Entropy-based Bias Reduction for Video-grounded Dialogue Generation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 2958–2968, Torino, Italia. ELRA and ICCL.
Cite (Informal):
CE-VDG: Counterfactual Entropy-based Bias Reduction for Video-grounded Dialogue Generation (Liu et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.264.pdf