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

13 Feb 2023  ·  Yongqi Li, Yu Yu, Tieyun Qian ·

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.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Few-shot NER Few-NERD (INTER) TadNER 5 way 1~2 shot 64.83±0.14 # 4
5 way 5~10 shot 72.12±0.12 # 4
10 way 1~2 shot 64.06±0.19 # 3
10 way 5~10 shot 69.94±0.15 # 3
Few-shot NER Few-NERD (INTRA) TadNER 5 way 1~2 shot 60.78±0.32 # 2
5 way 5~10 shot 67.94±0.17 # 2
10 way 1~2 shot 55.44±0.08 # 2
10 way 5~10 shot 60.87±0.22 # 3

Methods