软件导刊2024，Vol.23Issue(12)：82-91,10.DOI:10.11907/rjdk.232212
基于改进全局指针的惠企政策命名实体识别方法
Improved Global Pointer Based Named Entity Recognition Method for Enterprise-benefiting Policies
杨虔懿 1喻金平1
作者信息
- 1. 江西理工大学 信息工程学院,江西 赣州 341000
- 折叠
摘要
Abstract
Small and medium-sized enterprises play an important role in the national economy.In recent years,various preferential policies for enterprises introduced by the government have included key information for government decision-making.However,policy texts have com-plex structures,strong dependence on professional semantics,and contain noisy text and nested entities,making information extraction diffi-cult.Therefore,a named entity recognition model based on multi-level vocabulary global pointers and adversarial training is proposed.This model integrates the LEBERT model at the embedding layer to obtain the combined semantic representation of characters and vocabulary,and constructs a global entity matrix through global pointers to uniformly process flat and nested entities;Simultaneously introducing rotary posi-tion encoding to enhance the perception of position information,and combining it with adversarial training to enhance stability and robustness.The experimental results show that the F1 value of the model is 81.90%,which is 4.72%higher than the classical sequence annotation based model.The overall performance supports downstream task development.关键词
命名实体识别/惠企政策/预训练模型/全局指针/对抗训练Key words
named entity recognition/enterprise-benefiting policies/pre-training model/global pointer/adversarial training分类
信息技术与安全科学引用本文复制引用
杨虔懿,喻金平..基于改进全局指针的惠企政策命名实体识别方法[J].软件导刊,2024,23(12):82-91,10.
