Information Screening whilst Exploiting! Multimodal Relation Extraction with Feature Denoising and Multimodal Topic Modeling
Wu, Shengqiong, Fei, Hao, Cao, Yixin, Bing, Lidong, Chua, Tat-Seng
–arXiv.org Artificial Intelligence
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. Our codes are open at https://github.com/ChocoWu/MRE-ISE.
arXiv.org Artificial Intelligence
May-25-2023
- Country:
- North America > United States (0.14)
- Asia
- China (0.14)
- Singapore (0.04)
- Middle East > Israel
- Jerusalem District > Jerusalem (0.04)
- Genre:
- Research Report (0.82)
- Industry:
- Media (0.46)
- Technology:
- Information Technology
- Sensing and Signal Processing > Image Processing (1.00)
- Communications > Social Media (1.00)
- Artificial Intelligence
- Vision (1.00)
- Representation & Reasoning (1.00)
- Natural Language > Text Processing (0.67)
- Machine Learning > Neural Networks (0.67)
- Information Technology