arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.09314cs.CLcs.AIcs.MM
收藏

TOT:面向多模态仇恨检测的拓扑感知最优传输

TOT: Topology-Aware Optimal Transport For Multimodal Hate Detection

Aerospace Information Research Institute, Chinese Academy of Sciences(中国科学院空天信息创新研究院);University of Chinese Academy of Sciences(中国科学院大学)

Linhao Zhang, Li Jin, Xian Sun, Guangluan Xu, Zequn Zhang, Xiaoyu Li, Nayu Liu, Qing Liu, Shiyao Yan

AI总结:

针对表情包中隐性仇恨内容难识别及跨模态分布鸿沟问题,本文提出拓扑感知最优传输框架 TOT,通过核嵌入与二部图路径推理实现可解释的跨模态对齐,并在两个基准上达到最先进性能。

摘要:

多模态仇恨检测旨在识别在线有害内容(如表情包),对于构建健康的互联网环境至关重要。以往工作在检测显性仇恨言论方面进行了富有启发性的探索。然而,其大多数方法忽视了对隐性伤害的分析;由于显性文本标记和人口统计视觉线索常被扭曲或缺失,这一问题尤其具有挑战性。所采用的跨模态注意力机制也受限于分布层面的模态鸿沟,并缺乏逻辑可解释性。为解决这些语义鸿沟问题,我们提出 TOT:一个拓扑感知最优传输框架,用于解读表情包场景中的隐性伤害;该框架将跨模态对齐问题表述为最优传输计划的求解。具体而言,我们利用最优传输核方法捕获来自多种模态的互补信息。核嵌入提供非线性变换能力,以再生核 Hilbert 空间(RKHS),这对消除分布层面的模态鸿沟具有重要意义。此外,我们基于对齐后的表示感知拓扑信息,以进行二部图路径推理。在两个公开可用基准数据集上最新取得的最先进性能,连同进一步的可视化分析,证明了 TOT 在捕获隐性跨模态对齐方面的优越性。

英文摘要:

Multimodal hate detection, which aims to identify harmful content online such as memes, is crucial for building a wholesome internet environment. Previous work has made enlightening exploration in detecting explicit hate remarks. However, most of their approaches neglect the analysis of implicit harm, which is particularly challenging as explicit text markers and demographic visual cues are often twisted or missing. The leveraged cross-modal attention mechanisms also suffer from the distributional modality gap and lack logical interpretability. To address these semantic gaps issues, we propose TOT: a topology-aware optimal transport framework to decipher the implicit harm in memes scenario, which formulates the cross-modal aligning problem as solutions for optimal transportation plans. Specifically, we leverage an optimal transport kernel method to capture complementary information from multiple modalities. The kernel embedding provides a non-linear transformation ability to reproduce a kernel Hilbert space (RKHS), which reflects significance for eliminating the distributional modality gap. Moreover, we perceive the topology information based on aligned representations to conduct bipartite graph path reasoning. The newly achieved state-of-the-art performance on two publicly available benchmark datasets, together with further visual analysis, demonstrate the superiority of TOT in capturing implicit cross-modal alignment.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑