DAN: Dual-View Representation Learning for Adapting Stance Classifiers to New Domains

TL;DR

This paper introduces DAN, a dual-view learning approach that improves domain adaptation for stance classification by capturing distinct linguistic expressions, leading to better transferability and state-of-the-art performance.

Contribution

The paper proposes a novel dual-view adaptation network that separately models different stance expressions, enhancing domain transfer and outperforming single-view methods.

Findings

DAN outperforms existing methods in cross-domain stance classification.

The dual-view approach captures diverse stance expressions more effectively.

Combined views lead to more transferable and discriminative features.

Abstract

We address the issue of having a limited number of annotations for stance classification in a new domain, by adapting out-of-domain classifiers with domain adaptation. Existing approaches often align different domains in a single, global feature space (or view), which may fail to fully capture the richness of the languages used for expressing stances, leading to reduced adaptability on stance data. In this paper, we identify two major types of stance expressions that are linguistically distinct, and we propose a tailored dual-view adaptation network (DAN) to adapt these expressions across domains. The proposed model first learns a separate view for domain transfer in each expression channel and then selects the best adapted parts of both views for optimal transfer. We find that the learned view features can be more easily aligned and more stance-discriminative in either or both views, leading to more transferable overall features after combining the views. Results from extensive experiments show that our method can enhance the state-of-the-art single-view methods in matching stance data across different domains, and that it consistently improves those methods on various adaptation tasks.