MLSD通过度量学习提升跨目标跨领域立场检测效果。
MLSD: A Novel Few-Shot Learning Approach to Enhance Cross-Target and Cross-Domain Stance Detection
- 用三元组损失构建语义相似性空间，捕捉立场目标差异。
- 在六个主流模型上实现显著性能提升，跨域跨目标检测更准。
- 适合需要少样本快速适应新立场任务的研究者使用。
我们提出一种新型少样本学习方法——基于度量学习的跨目标与跨域立场检测（MLSD）。MLSD利用三元组损失进行度量学习，捕捉立场目标间的语义相似性与差异性，增强领域自适应能力。通过构建判别性嵌入空间，MLSD使跨目标或跨域立场检测模型能够从新目标领域中获取有用示例。我们在两个数据集上的多个跨目标和跨域场景中评估了MLSD，结果显示其在六种广泛使用的立场检测模型上均取得统计显著的性能提升。
原文摘要 · Abstract (English)
We present the novel approach for stance detection across domains and targets, Metric Learning-Based Few-Shot Learning for Cross-Target and Cross-Domain Stance Detection (MLSD). MLSD utilizes metric learning with triplet loss to capture semantic similarities and differences between stance targets, enhancing domain adaptation. By constructing a discriminative embedding space, MLSD allows a cross-target or cross-domain stance detection model to acquire useful examples from new target domains. We evaluate MLSD in multiple cross-target and cross-domain scenarios across two datasets, showing statistically significant improvement in stance detection performance across six widely used stance detection models.
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。