Multimodal Aspect-based Sentiment Analysis (MABSA) is a fine-grained Sentiment Analysis task, which has attracted growing research interests recently. Existing work mainly utilizes image information to improve the performance of MABSA task. However, most of the studies overestimate the importance of images since there are many noise images unrelated to the text in the dataset, which will have a negative impact on model learning. Although some work attempts to filter low-quality noise images by setting thresholds, relying on thresholds will inevitably filter out a lot of useful image information. Therefore, in this work, we focus on whether the negative impact of noisy images can be reduced without modifying the data. To achieve this goal, we borrow the idea of Curriculum Learning and propose a Multi-grained Multi-curriculum Denoising Framework (M2DF), which can achieve denoising by adjusting the order of training data. Extensive experimental results show that our framework consistently outperforms state-of-the-art work on three sub-tasks of MABSA.
@article{arxiv.2310.14605,
title = {M2DF: Multi-grained Multi-curriculum Denoising Framework for Multimodal Aspect-based Sentiment Analysis},
author = {Fei Zhao and Chunhui Li and Zhen Wu and Yawen Ouyang and Jianbing Zhang and Xinyu Dai},
journal= {arXiv preprint arXiv:2310.14605},
year = {2023}
}