SemEval2023 任务 1 中的 OPI: 面向视觉词义消歧的图像 - 文本嵌入和多模态信息检索【英文版】

英文标题：OPI at SemEval 2023 Task 1: Image-Text Embeddings and Multimodal Information Retrieval for Visual Word Sense Disambiguation中文摘要：本研究提出采用多模态模型、排序学习以及基于知识的方法来进行词义消歧，并在 SemEval 2023 视觉词义消歧共享任务中荣获波斯语赛道的冠军以及多语言赛道的第三名。英文摘要：The goal of visual word sense disambiguation is to find the image that bestmatches the provided description of the word's meaning. It is a challengingproblem, requiring approaches that combine language and image understanding. Inthis paper, we present our submission to SemEval