FUSE
发表于 2025-3-28 14:57:44
Unknown Intention Detection Method Based on Dynamic Constraint Boundary. On the other hand, identifying open (unknown) intent during testing. Current models are limited in finding the appropriate decision boundary to balance the performances of both known and open intents. In this chapter, a post-processing method is proposed to learn the adaptive decision boundary (AD
atopic-rhinitis
发表于 2025-3-28 22:00:46
http://reply.papertrans.cn/48/4704/470333/470333_42.png
defile
发表于 2025-3-29 01:03:19
Discovering New Intents with Deep Aligned Clusterings to new intents. These methods also have difficulties in providing high-quality supervised signals to learn clustering-friendly features for grouping unlabeled intents. In this work, we introduce an effective method (Deep Aligned Clustering) to discover new intents with the aid of limited known int
ESO
发表于 2025-3-29 05:39:28
http://reply.papertrans.cn/48/4704/470333/470333_44.png
大暴雨
发表于 2025-3-29 09:50:35
http://reply.papertrans.cn/48/4704/470333/470333_45.png
Interregnum
发表于 2025-3-29 13:49:41
http://reply.papertrans.cn/48/4704/470333/470333_46.png
Inculcate
发表于 2025-3-29 19:18:07
http://reply.papertrans.cn/48/4704/470333/470333_47.png