LA-HCN: Label-based Attention for Hierarchical Multi-label Text Classification Neural Network

作者：

Highlights：

• Proposed label-based attention can improve performance and provide interpretability.

• Information can be shared across hierarchical layers while avoiding error propagation.

• Respective document embedding is generated for local and global classification to prevent error propagation.

摘要

•Proposed label-based attention can improve performance and provide interpretability.•Information can be shared across hierarchical layers while avoiding error propagation.•Respective document embedding is generated for local and global classification to prevent error propagation.

论文关键词：NLP,Deep neural network,HMTC,Multi-label text classification,Attention

论文评审过程：Received 17 January 2021, Revised 14 May 2021, Accepted 15 September 2021, Available online 29 September 2021, Version of Record 4 October 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115922