Noun-based attention mechanism for Fine-grained Named Entity Recognition

作者：

Highlights：

• FgED system that combines BPEmb Vectors with Flair Language Models.

• Attention mechanism based on the syntactic type of the words, specifically on nouns.

• FgET architecture that integrates BPEmb Vectors with: ELMo, Flair, and BERT.

• Evaluates the performance of each contextual embedding and network components.

摘要

•FgED system that combines BPEmb Vectors with Flair Language Models.•Attention mechanism based on the syntactic type of the words, specifically on nouns.•FgET architecture that integrates BPEmb Vectors with: ELMo, Flair, and BERT.•Evaluates the performance of each contextual embedding and network components.

论文关键词：Fine-grained Named Entity Recognition,Entity detection,Entity typing,Noun-based attention mechanism

论文评审过程：Received 3 March 2021, Revised 11 October 2021, Accepted 11 December 2021, Available online 6 January 2022, Version of Record 18 January 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.116406