EDDA: A Encoder-Decoder Data Augmentation Framework for Zero-Shot Stance Detection

arXiv:2403.15715v1 Announce Type: new
Abstract: Stance detection aims to determine the attitude expressed in text towards a given target. Zero-shot stance detection (ZSSD) has emerged to classify stances towards unseen targets during inference. Recent data augmentation techniques for ZSSD increase transferable knowledge between targets through text or target augmentation. However, these methods exhibit limitations. Target augmentation lacks logical connections between generated targets and source text, while text augmentation relies solely on training data, resulting in insufficient generalization. To address these …

abstract arxiv attitude augmentation cs.cl data decoder detection encoder encoder-decoder framework however inference knowledge targets text through type zero-shot