On Analyzing the Role of Image for Visual-enhanced Relation Extraction

Li, Lei, Chen, Xiang, Qiao, Shuofei, Xiong, Feiyu, Chen, Huajun, Zhang, Ningyu

arXiv.org Artificial Intelligence 

Multimodal relation extraction is an essential task for knowledge graph construction. In this paper, we take an in-depth empirical analysis that indicates the inaccurate information in the visual scene graph leads to poor modal alignment weights, further degrading performance. Moreover, the visual shuffle experiments illustrate that the current approaches may not take full advantage of visual information. Based on the above observation, we further propose a strong baseline with an implicit fine-grained multimodal alignment based on Transformer for multimodal relation extraction. Experimental results demonstrate the better performance of our method. Codes are available at https://github.com/zjunlp/DeepKE/tree/main/example/re/multimodal.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found