Type-Aware Decomposed Framework for Few-Shot Named Entity Recognition

TL;DR

TadNER introduces a type-aware decomposed framework for few-shot NER that effectively filters false spans and constructs stable prototypes, achieving state-of-the-art results.

Contribution

The paper proposes a novel type-aware span filtering and contrastive learning strategy to improve few-shot NER performance.

Findings

Achieves new state-of-the-art on various benchmarks.

Effectively filters false spans using semantic distance to type names.

Constructs more accurate and stable prototypes with joint support and type name references.

Abstract

Despite the recent success achieved by several two-stage prototypical networks in few-shot named entity recognition (NER) task, the overdetected false spans at the span detection stage and the inaccurate and unstable prototypes at the type classification stage remain to be challenging problems. In this paper, we propose a novel Type-Aware Decomposed framework, namely TadNER, to solve these problems. We first present a type-aware span filtering strategy to filter out false spans by removing those semantically far away from type names. We then present a type-aware contrastive learning strategy to construct more accurate and stable prototypes by jointly exploiting support samples and type names as references. Extensive experiments on various benchmarks prove that our proposed TadNER framework yields a new state-of-the-art performance. Our code and data will be available at https://github.com/NLPWM-WHU/TadNER.