从因果视角缓解灾难事件数据偏差，提升模型泛化能力。
Generalizing to Unseen Disaster Events: A Causal View
- 基于因果学习构建去偏框架，分离事件与领域相关噪声
- 在3个灾难分类任务中提升最多1.9% F1值
- 适合需要跨事件泛化的灾难监测系统开发者
随着社交媒体平台的迅速发展，这些工具已成为实时监控灾难事件信息的关键手段。然而，从中提取有效洞察需要对海量数据进行实时处理。现有系统面临事件相关偏差问题，严重影响其对新发事件的泛化能力。尽管去偏和因果学习技术已取得进展，但在灾难事件领域仍研究不足。本文从因果视角出发，提出一种减少事件与领域相关偏差的方法，显著提升模型对未来事件的泛化性能。实验表明，该方法在三个灾难分类任务中优于多个基线模型，最大提升达+1.9% F1，同时显著改善了PLM-based分类器的表现。
原文摘要 · Abstract (English)
Due to the rapid growth of social media platforms, these tools have become essential for monitoring information during ongoing disaster events. However, extracting valuable insights requires real-time processing of vast amounts of data. A major challenge in existing systems is their exposure to event-related biases, which negatively affects their ability to generalize to emerging events. While recent advancements in debiasing and causal learning offer promising solutions, they remain underexplored in the disaster event domain. In this work, we approach bias mitigation through a causal lens and propose a method to reduce event- and domain-related biases, enhancing generalization to future events. Our approach outperforms multiple baselines by up to +1.9% F1 and significantly improves a PLM-based classifier across three disaster classification tasks.
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。