Category-learning attention mechanism for short text filtering

Neurocomputing（2022）

Cited 2|Views1

No score

Abstract

•A novel category-learning attention mechanism is proposed.•It includes category-learning scaled-dot-product attention mechanism.•It includes category-learning multi-head attention mechanism (CL-MHA).•The attention mechanisms build category differentiation feature matrices dynamically.•The CL-MHA based bidirectional gate recurrent unit achieves the best performance.

Translated text

Key words

Short message classification,Multi-head attention,Bidirectional gate recurrent unit,Category-learning attention,Category-learning multi-head attention

AI Read Science

Must-Reading Tree

Example

Generate MRT to find the research sequence of this paper

Chat Paper

Summary is being generated by the instructions you defined