摘要
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.
作者
孙鹏飞
欧阳亚文
宋定杰
戴新宇
Peng-Fei Sun;Ya-Wen Ouyang;Ding-Jie Song;Xin-Yu Dai(National Key Laboratory for Novel Software Technology,Nanjing University,Nanjing 210093,China)
基金
the National Natural Science Foundation of China under Grant Nos.61936012 and 61976114。