@article{Sun2022, 
author = {Peng-Fei Sun and Ya-Wen Ouyang and Ding-Jie Song and Xin-Yu Dai},
title = {Self-Supervised Task Augmentation for Few-Shot Intent Detection},
year = {2022},
journal = {Journal of Computer Science and Technology},
volume = {37},
number = {3},
pages = {527-538},
keywords = {self-supervised learning, task augmentation, meta-learning, few-shot intent detection},
url = {https://www.sciopen.com/article/10.1007/s11390-022-2029-5},
doi = {10.1007/s11390-022-2029-5},
abstract = {Few-shot intent detection is a practical challenge task, because new intents are frequently emerging and collecting large-scale data for them could be costly. Meta-learning, a promising technique for leveraging data from previous tasks to enable efficient learning of new tasks, has been a popular way to tackle this problem. However, the existing meta-learning models have been evidenced to be overfitting when the meta-training tasks are insufficient. To overcome this challenge, we present a novel self-supervised task augmentation with meta-learning framework, namely STAM. Firstly, we introduce the task augmentation, which explores two different strategies and combines them to extend meta-training tasks. Secondly, we devise two auxiliary losses for integrating self-supervised learning into meta-learning to learn more generalizable and transferable features. Experimental results show that STAM can achieve consistent and considerable performance improvement to existing state-of-the-art methods on four datasets.}
}