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

Daijun Ding, Li Dong, Zhichao Huang, Guangning Xu, Xu Huang, Bo Liu, Liwen Jing, Bowen Zhang


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 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.
Anthology ID:
2024.lrec-main.487
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
5484–5494
Language:
URL:
https://aclanthology.org/2024.lrec-main.487
DOI:
Bibkey:
Cite (ACL):
Daijun Ding, Li Dong, Zhichao Huang, Guangning Xu, Xu Huang, Bo Liu, Liwen Jing, and Bowen Zhang. 2024. EDDA: An Encoder-Decoder Data Augmentation Framework for Zero-Shot Stance Detection. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 5484–5494, Torino, Italia. ELRA and ICCL.
Cite (Informal):
EDDA: An Encoder-Decoder Data Augmentation Framework for Zero-Shot Stance Detection (Ding et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.487.pdf