EDDA: A Encoder-Decoder Data Augmentation Framework for Zero-Shot Stance Detection
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 issues, we propose an encoder-decoder data augmentation (EDDA) framework. The encoder leverages large language models and chain-of-thought prompting to summarize texts into target-specific if-then rationales, establishing logical relationships. The decoder generates new samples based on these expressions using a semantic correlation word replacement strategy to increase syntactic diversity. We also analyze the generated expressions to develop a rationale-enhanced network that fully utilizes the augmented data. Experiments on benchmark datasets demonstrate our approach substantially improves over state-of-the-art ZSSD techniques. The proposed EDDA framework increases semantic relevance and syntactic variety in augmented texts while enabling interpretable rationale-based learning.
Code (1)
Tasks
Data AugmentationDecoderDiversityStance DetectionText AugmentationZero-Shot Stance DetectionSimilar Papers 제목 키워드 기반
FedDAG: Clustered Federated Learning via Global Data and Gradient Integration for Heterogeneous Environments
Federated Learning (FL) enables a group of clients to collaboratively train a model without sharing individual data, but its performance drops when client data are heterogeneous. Clustered FL tackles this by grouping sim…
Federated LearningEDDA: Explanation-driven Data Augmentation to Improve Explanation Faithfulness
Recent years have seen the introduction of a range of methods for post-hoc explainability of image classifier predictions. However, these post-hoc explanations may not always be faithful to classifier predictions, which …
Data Augmentationimage-classificationImage ClassificationPredictionTAMISeg: Text-Aligned Multi-scale Medical Image Segmentation with Semantic Encoder Distillation
Medical image segmentation remains challenging due to limited fine-grained annotations, complex anatomical structures, and image degradation from noise, low contrast, or illumination variation. We propose TAMISeg, a text…
Medical Image SegmentationImage Captioning using Deep Stacked LSTMs, Contextual Word Embeddings and Data Augmentation
Image Captioning, or the automatic generation of descriptions for images, is one of the core problems in Computer Vision and has seen considerable progress using Deep Learning Techniques. We propose to use Inception-ResN…
Data AugmentationDecoderImage CaptioningWord EmbeddingsPersonalized Federated Collaborative Filtering: A Variational AutoEncoder Approach
Federated Collaborative Filtering (FedCF) is an emerging field focused on developing a new recommendation framework with preserving privacy in a federated setting. Existing FedCF methods typically combine distributed Col…
Collaborative FilteringDecoderPrivacy PreservingValue prediction