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

TL;DR

This paper introduces MsFNER, a hybrid multi-stage decoding approach with entity-aware contrastive learning for few-shot NER, improving entity detection and classification efficiency across domains.

Contribution

The paper proposes a novel two-stage framework with contrastive learning for few-shot NER, reducing computational load and enhancing cross-domain entity recognition performance.

Findings

Outperforms existing methods on FewNERD dataset

Effective entity span detection and classification in few-shot scenarios

Demonstrates robustness across different domains

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: training, finetuning, and inference. In the training process, we train and get the best entity-span detection model and the entity classification model separately on the source domain using meta-learning, where we create a contrastive learning module to enhance entity representations for entity classification. During finetuning, we finetune the both models on the support dataset of target domain. In the inference process, for the unlabeled data, we first detect the entity-spans, then the entity-spans are jointly determined by the entity classification model and the KNN. We conduct experiments on the open FewNERD dataset and the results demonstrate the advance of MsFNER.