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

扫码查看

原文链接

NETL
NSTL
万方数据

外文摘要：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 uti-lize 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.

外文关键词：

named entity recognitionprototypical networkspatial relationmultidimensional convolution

作者：

LIU Zhiwei、HUANG Bo、XIA Chunming、XIONG Yujie、ZANG Zhensen、ZHANG Yongqiang

展开 >

作者单位：

College of Electrical and Electronic Engineering,Shanghai University of Engineering Science,Shanghai 201620,China

Shanghai Zhongyu Academy of Industrial Internet,Shanghai 201620,China

AIoT Manufacturing Solutions Technology Co.,Ltd.,Hefei 230000,Anhui,China

基金：

Scientific and Technological Innovation 2030-Major Project of New Generation Artificial Intelligencescience and Technology Commission of Shanghai Municipality2023 Anhui Province Key Research and Development Plan Project-Special Project of Science and Technology Cooperation

项目编号：

2020AAA010930021DZ22031002023i11020002

出版年：

2024

DOI：

10.1051/wujns/2024292125

武汉大学自然科学学报(英文版)

武汉大学

武汉大学自然科学学报(英文版)

CSTPCD

影响因子：0.066

ISSN：1007-1202

年,卷(期)：2024.29(2)

参考文献量38