Computer Science

CLC number: TP391.1

Few-Shot Named Entity Recognition with the Integration of Spatial Features

¹ College of Electrical and Electronic Engineering, Shanghai University of Engineering Science, Shanghai 201620, China
² Shanghai Zhongyu Academy of Industrial Internet, Shanghai 201620, China
³ AIoT Manufacturing Solutions Technology Co., Ltd., Hefei 230000, Anhui, China

^† Corresponding author. E-mail: huangbosues@sues.edu.cn

Received: 28 December 2023

Abstract

The few-shot named entity recognition (NER) task aims to train a robust model in the source domain and transfer it to the target domain with very few annotated data. Currently, some approaches rely on the prototypical network for NER. However, these approaches often overlook the spatial relations in the span boundary matrix because entity words tend to depend more on adjacent words. We propose using a multidimensional convolution module to address this limitation to capture short-distance spatial dependencies. Additionally, we utilize an improved prototypical network and assign different weights to different samples that belong to the same class, thereby enhancing the performance of the few-shot NER task. Further experimental analysis demonstrates that our approach has significantly improved over baseline models across multiple datasets.