Zero-Shot Stance Detection: A Dataset and Model using Generalized Topic Representations

TL;DR

This paper introduces a new dataset and a novel model for zero-shot stance detection that effectively handles diverse topics and linguistic variations, advancing the ability to classify stances without prior training data.

Contribution

The paper provides a comprehensive dataset for zero-shot stance detection and proposes a model that leverages generalized topic representations to improve classification accuracy.

Findings

The new dataset covers a wider range of topics and lexical variations.

The proposed model outperforms existing approaches on challenging linguistic phenomena.

Generalized topic representations enhance zero-shot stance detection performance.

Abstract

Stance detection is an important component of understanding hidden influences in everyday life. Since there are thousands of potential topics to take a stance on, most with little to no training data, we focus on zero-shot stance detection: classifying stance from no training examples. In this paper, we present a new dataset for zero-shot stance detection that captures a wider range of topics and lexical variation than in previous datasets. Additionally, we propose a new model for stance detection that implicitly captures relationships between topics using generalized topic representations and show that this model improves performance on a number of challenging linguistic phenomena.