典型文献
Improving entity linking with two adaptive features
文献摘要：
Entity linking (EL) is a fundamental task in natural language processing. Based on neural networks, existing systems pay more attention to the construction of the global model, but ignore latent semantic information in the local model and the acquisition of effective entity type information. In this paper, we propose two adaptive features, in which the fi rst adaptive feature enables the local and global models to capture latent information, and the second adaptive feature describes effective information for entity type embeddings. These adaptive features can work together naturally to handle some uncertain entity type information for EL. Experimental results demonstrate that our EL system achieves the best performance on the AIDA-B and MSNBC datasets, and the best average performance on out-domain datasets. These results indicate that the proposed adaptive features, which are based on their own diverse contexts, can capture information that is conducive for EL.
文献关键词：
中图分类号：
作者姓名：
Hongbin ZHANG;Quan CHEN;Weiwen ZHANG
作者机构：
School of Computer Science and Technology,Guangdong University of Technology,Guangzhou 510006,China
文献出处：
引用格式：
[1]Hongbin ZHANG;Quan CHEN;Weiwen ZHANG-.Improving entity linking with two adaptive features)[J].信息与电子工程前沿（英文）,2022(11):1620-1630
A类：
MSNBC
B类：
Improving,entity,linking,adaptive,features,Entity,EL,fundamental,task,language,processing,Based,neural,networks,existing,systems,pay,more,attention,construction,global,but,ignore,latent,semantic,information,local,acquisition,effective,type,In,this,paper,we,which,fi,rst,enables,models,capture,second,describes,embeddings,These,can,together,naturally,handle,some,uncertain,Experimental,results,demonstrate,that,our,achieves,best,performance,AIDA,datasets,average,out,domain,indicate,proposed,are,their,own,diverse,contexts,conducive
AB值：
0.54276
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
