← Search

QiXiang Gao

2 accepted papers

2023

A Prototypical Semantic Decoupling Method via Joint Contrastive Learning for Few-Shot Named Entity Recognition

ICASSP 2023accepted

Few-shot named entity recognition (NER) aims at identifying named entities based on only few labeled instances. Most existing prototype-based sequence labeling models tend to memorize entity mentions which would be easily confused by close prototypes. In this paper, we proposed a Prototypical Semant…

Cited by 0SourceScholar
2022

Revisit Overconfidence for OOD Detection: Reassigned Contrastive Learning with Adaptive Class-dependent Threshold

NAACL 2022long

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 the overconfidence of neural models. In this paper, we comprehensively analyze overconfidence and classify it into two perspectives: over-confident OO…