Cross-Target Stance Classification with Self-Attention Networks

TL;DR

This paper proposes a neural model for cross-target stance classification that leverages shared information between different targets to improve generalization across diverse stance prediction tasks.

Contribution

It introduces a neural approach that enables transfer learning between targets in stance classification, enhancing model adaptability and performance.

Findings

Model effectively transfers knowledge between targets.

Shared information improves classification accuracy.

Approach outperforms target-specific models in some scenarios.

Abstract

In stance classification, the target on which the stance is made defines the boundary of the task, and a classifier is usually trained for prediction on the same target. In this work, we explore the potential for generalizing classifiers between different targets, and propose a neural model that can apply what has been learned from a source target to a destination target. We show that our model can find useful information shared between relevant targets which improves generalization in certain scenarios.