Unseen Target Stance Detection with Adversarial Domain Generalization

Abstract

Although stance detection has made great progress in the past few years, it\nis still facing the problem of unseen targets. In this study, we investigate\nthe domain difference between targets and thus incorporate attention-based\nconditional encoding with adversarial domain generalization to perform unseen\ntarget stance detection. Experimental results show that our approach achieves\nnew state-of-the-art performance on the SemEval-2016 dataset, demonstrating the\nimportance of domain difference between targets in unseen target stance\ndetection.\n