Unseen Target Stance Detection with Adversarial Domain Generalization

Abstract

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

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Neural Machine Translation by Jointly Learning to Align and Translate
• Domain Generalization via Invariant Feature Representation
• Adversarial Discriminative Domain Adaptation
• Adversarial Learning for Neural Dialogue Generation
• Adversarial Multi-Criteria Learning for Chinese Word Segmentation
• Adversarial Domain Adaptation for Stance Detection
• Adversarial Learning for Chinese NER from Crowd Annotations
• Rethinking Generalization of Neural Models: A Named Entity Recognition Case Study
• Robust Semantic Parsing with Adversarial Learning for Domain Generalization
• Cross-Domain Generalization of Neural Constituency Parsers

Cited by in corpus (5)

• Single-source Domain Expansion Network for Cross-Scene Hyperspectral Image Classification
• Towards Out-Of-Distribution Generalization: A Survey
• Understanding and Testing Generalization of Deep Networks on Out-of-Distribution Data
• University of Copenhagen Participation in TREC Health Misinformation Track 2020
• Human-in-the-Loop Disinformation Detection: Stance, Sentiment, or Something Else?