Hybrid Multi-stage Decoding for Few-shot NER with Entity-aware Contrastive Learning

arXiv:2404.06970v1 Announce Type: new
Abstract: Few-shot named entity recognition can identify new types of named entities based on a few labeled examples. Previous methods employing token-level or span-level metric learning suffer from the computational burden and a large number of negative sample spans. In this paper, we propose the Hybrid Multi-stage Decoding for Few-shot NER with Entity-aware Contrastive Learning (MsFNER), which splits the general NER into two stages: entity-span detection and entity classification. There are 3 processes for introducing MsFNER: …

abstract arxiv computational cs.cl decoding examples few-shot hybrid identify negative ner paper recognition sample stage token type types