通过自适应对比学习提升隐性性别歧视检测精度。
An Adaptive Supervised Contrastive Learning Framework for Implicit Sexism Detection in Digital Social Networks
- 基于可学习阈值的对比学习，只将高相似度样本对视为正例。
- 在多个任务上平均宏F1提升最高达32.51%。
- 适合需要精准识别隐性偏见的社交内容安全场景。
社交媒体的全球传播加剧了仇恨内容的扩散，包括常被传统方法忽略的隐性性别歧视。本文提出一种自适应监督对比学习框架ASCEND。其核心是阈值驱动的对比学习：通过计算嵌入向量的余弦相似度，仅当相似度超过可学习阈值时才将样本对视为正例。该机制有效优化嵌入空间，增强语义相近文本的聚类，同时拉开不相似样本的距离，显著减少误检与漏检。分类阶段联合优化对比损失与交叉熵损失。文本特征通过词级注意力模块增强，并融合情感、情绪及毒性特征。在EXIST2021和MLSC数据集上的实验表明，ASCEND在多项任务中平均宏F1分别提升9.86%、29.63%和32.51%，验证了其捕捉隐性性别歧视细微线索的有效性。
原文摘要 · Abstract (English)
The global reach of social media has amplified the spread of hateful content, including implicit sexism, which is often overlooked by conventional detection methods. In this work, we introduce an Adaptive Supervised Contrastive lEarning framework for implicit sexism detectioN (ASCEND). A key innovation of our method is the incorporation of threshold-based contrastive learning: by computing cosine similarities between embeddings, we selectively treat only those sample pairs as positive if their similarity exceeds a learnable threshold. This mechanism refines the embedding space by robustly pulling together representations of semantically similar texts while pushing apart dissimilar ones, thus reducing false positives and negatives. The final classification is achieved by jointly optimizing a contrastive loss with a cross-entropy loss. Textual features are enhanced through a word-level attention module. Additionally, we employ sentiment, emotion, and toxicity features. Evaluations on the EXIST2021 and MLSC datasets demonstrate that ASCEND significantly outperforms existing methods, with average Macro F1 improvements of 9.86%, 29.63%, and 32.51% across multiple tasks, highlighting its efficacy in capturing the subtle cues of implicit sexist language.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。