Information Screening whilst Exploiting! Multimodal Relation Extraction with Feature Denoising and Multimodal Topic Modeling

Shengqiong Wu, Hao Fei, Yixin Cao, Lidong Bing, Tat-Seng Chua


Abstract
Existing research on multimodal relation extraction (MRE) faces two co-existing challenges, internal-information over-utilization and external-information under-exploitation. To combat that, we propose a novel framework that simultaneously implements the idea of internal-information screening and external-information exploiting. First, we represent the fine-grained semantic structures of the input image and text with the visual and textual scene graphs, which are further fused into a unified cross-modal graph (CMG). Based on CMG, we perform structure refinement with the guidance of the graph information bottleneck principle, actively denoising the less-informative features. Next, we perform topic modeling over the input image and text, incorporating latent multimodal topic features to enrich the contexts. On the benchmark MRE dataset, our system outperforms the current best model significantly. With further in-depth analyses, we reveal the great potential of our method for the MRE task.
Anthology ID:
2023.acl-long.823
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14734–14751
Language:
URL:
https://aclanthology.org/2023.acl-long.823
DOI:
10.18653/v1/2023.acl-long.823
Bibkey:
Cite (ACL):
Shengqiong Wu, Hao Fei, Yixin Cao, Lidong Bing, and Tat-Seng Chua. 2023. Information Screening whilst Exploiting! Multimodal Relation Extraction with Feature Denoising and Multimodal Topic Modeling. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 14734–14751, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Information Screening whilst Exploiting! Multimodal Relation Extraction with Feature Denoising and Multimodal Topic Modeling (Wu et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/2023.acl-long.823.pdf
Video:
 https://preview.aclanthology.org/improve-issue-templates/2023.acl-long.823.mp4