paper-with-me

Papers

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

2024-03-23 · Daijun Ding, Li Dong, Zhichao Huang, Guangning Xu, Xu Huang, Bo Liu, Liwen Jing, BoWen Zhang

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.

📄 PDF Abstract BibTeX arXiv:2403.15715

Code (1)

szu-ddj/edda 공식 구현 pytorch

Tasks

Data AugmentationDecoderDiversityStance DetectionText AugmentationZero-Shot Stance Detection

Similar Papers 제목 키워드 기반

FedDAG: Clustered Federated Learning via Global Data and Gradient Integration for Heterogeneous Environments

2026-02-26 · Anik Pramanik, Murat Kantarcioglu, Vincent Oria, Shantanu Sharma arxiv

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 Learning

EDDA: Explanation-driven Data Augmentation to Improve Explanation Faithfulness

2021-05-29 · Ruiwen Li, Zhibo Zhang, Jiani Li, Chiheb Trabelsi 외

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 ClassificationPrediction

TAMISeg: Text-Aligned Multi-scale Medical Image Segmentation with Semantic Encoder Distillation

2026-04-13 · Qiang Gao, Yi Wang, Yong Zhang, Yong Li 외 arxiv

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 Segmentation

Image Captioning using Deep Stacked LSTMs, Contextual Word Embeddings and Data Augmentation

2021-02-22 · Sulabh Katiyar, Samir Kumar Borgohain

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 Embeddings

Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approach

2024-08-16 · Zhiwei Li, Guodong Long, Tianyi Zhou, Jing Jiang 외

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