most citedModeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning

2 citations · 2 across the 2 of their papers we have counts for

collaborators
Showing cs.CLShow all

2 papers · 1 filter

cs.CL2021

Novel Slot Detection: A Benchmark for Discovering Unknown Slot Types in the Task-Oriented Dialogue System

Yanan Wu, Zhiyuan Zeng, Keqing He +4

Existing slot filling models can only recognize pre-defined in-domain slot types from a limited slot set. In the practical application, a reliable dialogue system should know what…

cs.CL2021★ 2 cited

Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning

Zhiyuan Zeng, Keqing He, Yuanmeng Yan +5

Detecting Out-of-Domain (OOD) or unknown intents from user queries is essential in a task-oriented dialog system. A key challenge of OOD detection is to learn discriminative semant…