Zero-Shot Stance Detection: A Dataset and Model using Generalized Topic Representations
This work addresses the problem of stance detection for topics with little to no training data, which is incremental as it builds on existing zero-shot methods with a new dataset and model.
The paper tackles zero-shot stance detection by introducing a new dataset with broader topic coverage and lexical variation, and proposes a model using generalized topic representations that improves performance on challenging linguistic phenomena.
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.