A meta-contrastive learning with data augmentation framework for zero-shot stance detection
Zero-shot stance detection (ZSSD) identifies the stances of targets that have not been encountered during the testing phase. Most of the existing efforts are dedicated to enhancing the generalizability of models while ignoring data issues such as data scarcity and targets that are not explicitly men...
Saved in:
Published in | Expert systems with applications Vol. 250; p. 123956 |
---|---|
Main Authors | , , |
Format | Journal Article |
Language | English |
Published |
Elsevier Ltd
15.09.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Zero-shot stance detection (ZSSD) identifies the stances of targets that have not been encountered during the testing phase. Most of the existing efforts are dedicated to enhancing the generalizability of models while ignoring data issues such as data scarcity and targets that are not explicitly mentioned. Therefore, we consider approaching this task from both the data and model perspectives and propose a meta-contrastive learning with data augmentation framework. We first use a generation model to generate target keyphrases for enhancing the original text. Then, we utilize a meta-learning technique that incorporates contrastive learning for improving the generalizability of the model, enabling it to better adapt to unknown targets. The experimental results obtained on three benchmark datasets prove that our framework achieves outstanding performance improvements in the ZSSD task. Our code is available at https://github.com/qifen37/MCLDA.
•Considering data scarcity and model generalizability for zero-shot stance detection.•Employing a generation model to produce target keyphrases for data augmentation.•Utilizing meta-contrastive learning to enhance the model’s generalizability.•Achieving state-of-the-art performance on multiple datasets. |
---|---|
ISSN: | 0957-4174 |
DOI: | 10.1016/j.eswa.2024.123956 |