Multimodal relation extraction with cross-modal retrieval and synthesis
Abstract
Multimodal relation extraction (MRE)is the task of identifying the semantic relationships between two entities based on the context of the sentence image pair.Existing retrievalaugmented approaches mainly focused on modeling the retrieved textual knowledge, but this may not be able to accurately identify complex relations.To improve the prediction, this research proposes to retrieve textual and visual evidence based on the object, sentence, and whole image.We further develop a novel approach to synthesize the object-level, imagelevel, and sentence-level information for better reasoning between the same and different modalities.Extensive experiments and analyses show that the proposed method is able to effectively select and compare evidence across modalities and significantly outperforms stateof-the-art models.Code and data are available 1 .
Authors: Xuming Hu, Zhijiang Guo, Zhiyang Teng, Irwin King, Philip S. Yu
Published in: Annual Meeting of the Association for Computational Linguistics (ACL) (2023)