典型文献
Self-Supervised Task Augmentation for Few-Shot Intent Detection
文献摘要：
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.
文献关键词：
中图分类号：
作者姓名：
Peng-Fei Sun;Ya-Wen Ouyang;Ding-Jie Song;Xin-Yu Dai
作者机构：
National Key Laboratory for Novel Software Technology,Nanjing University,Nanjing 210093,China
文献出处：
引用格式：
[1]Peng-Fei Sun;Ya-Wen Ouyang;Ding-Jie Song;Xin-Yu Dai-.Self-Supervised Task Augmentation for Few-Shot Intent Detection)[J].计算机科学技术学报（英文版）,2022(03):527-538
A类：
intents,STAM
B类：
Self,Supervised,Task,Augmentation,Few,Shot,Intent,Detection,shot,detection,practical,challenge,because,new,are,frequently,emerging,collecting,large,scale,them,could,costly,learning,promising,technique,leveraging,from,previous,tasks,enable,efficient,has,been,popular,way,tackle,this,problem,However,existing,meta,models,have,evidenced,overfitting,when,training,insufficient,To,overcome,present,novel,self,supervised,augmentation,framework,namely,Firstly,introduce,which,explores,two,different,strategies,combines,extend,Secondly,devise,auxiliary,losses,integrating,into,more,generalizable,transferable,features,Experimental,results,show,that,can,achieve,consistent,considerable,performance,improvement,state,art,methods,four,datasets
AB值：
0.640974
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
