MEAFE utilizes multi-modal pre-training models, OCR models, and GATv2 networks to enhance the information extraction ability of entity structure triplets and image descriptions, respectively obtaining more effective multi-modal representations, and analyzing the modal distribution of entities to enhance the modeling ability and understanding of entity information. Experiments on cross-language and cross-graph multi-modal datasets show that this method outperforms models that use traditional feature extraction.

翻译成英文:MEAFE使用多模预训练模型OCR模型GATv2网络提高的信息提取能力实体结构三联体和图像描述分别获得更有效的多模态表示并分析实体的模态分布以增强模型的建模能力理解实体信息。在跨语言和跨图多模态数据集上的实验表明该方法优于使用传统特征提取的模型

原文地址: https://www.cveoy.top/t/topic/bsu5 著作权归作者所有。请勿转载和采集!

免费AI点我,无需注册和登录