SOTAVerified

Few-shot NER

Few-Shot Named Entity Recognition (NER) is the task of recognising a 'named entity' like a person, organization, time and so on in a piece of text e.g. "Alan Mathison [person] visited the Turing Institute [organization] in June [time].

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–63 of 63 papers

TitleStatusHype
Hybrid Multi-stage Decoding for Few-shot NER with Entity-aware Contrastive Learning—0
PromptNER: Prompting For Named Entity Recognition—0
KnowDA: All-in-One Knowledge Mixture Model for Data Augmentation in Low-Resource NLP—0
SpanProto: A Two-stage Span-based Prototypical Network for Few-shot Named Entity Recognition—0
Large-Scale Label Interpretation Learning for Few-Shot Named Entity Recognition—0
LLM-DA: Data Augmentation via Large Language Models for Few-Shot Named Entity Recognition—0
llmNER: (Zero|Few)-Shot Named Entity Recognition, Exploiting the Power of Large Language Models—0
A Unified Label-Aware Contrastive Learning Framework for Few-Shot Named Entity Recognition—0
Causal Interventions-based Few-Shot Named Entity Recognition—0
CLLMFS: A Contrastive Learning enhanced Large Language Model Framework for Few-Shot Named Entity Recognition—0
CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning—0
ContrastNER: Contrastive-based Prompt Tuning for Few-shot NER—0
A Prototypical Semantic Decoupling Method via Joint Contrastive Learning for Few-Shot Name Entity Recognition—0
Show:102550
← PrevPage 3 of 3Next →

No leaderboard results yet.