Euphemism identification deciphers the true meaning of euphemisms, such as linking "weed" (euphemism) to "marijuana" (target keyword) in illicit texts, aiding content moderation and combating underground markets. While existing methods are primarily text-based, the rise of social media highlights the need for multimodal analysis, incorporating text, images, and audio. However, the lack of multimodal datasets for euphemisms limits further research. To address this, we regard euphemisms and their corresponding target keywords as keywords and first introduce a keyword-oriented multimodal corpus of euphemisms (KOM-Euph), involving three datasets (Drug, Weapon, and Sexuality), including text, images, and speech. We further propose a keyword-oriented multimodal euphemism identification method (KOM-EI), which uses cross-modal feature alignment and dynamic fusion modules to explicitly utilize the visual and audio features of the keywords for efficient euphemism identification. Extensive experiments demonstrate that KOM-EI outperforms state-of-the-art models and large language models, and show the importance of our multimodal datasets.

翻译：委婉语识别旨在解析委婉语的真实含义，例如在非法文本中将"weed"（委婉语）关联到"marijuana"（目标关键词），以辅助内容审核并打击地下市场。现有方法主要基于文本，而社交媒体的兴起凸显了融合文本、图像和音频的多模态分析的必要性。然而，委婉语多模态数据集的缺乏限制了进一步研究。为此，我们将委婉语及其对应的目标关键词视为关键词，首次构建了一个面向关键词的委婉语多模态语料库（KOM-Euph），包含三个数据集（毒品、武器和性相关），涵盖文本、图像和语音。我们进一步提出了一种面向关键词的多模态委婉语识别方法（KOM-EI），该方法通过跨模态特征对齐和动态融合模块，显式利用关键词的视觉和音频特征以实现高效的委婉语识别。大量实验表明，KOM-EI 优于现有最先进模型及大语言模型，并验证了我们多模态数据集的重要性。