,

Zhihao Yao1, Bo Li1, Yufei Liao1

  • 1The Key laboratory of Intelligent Technology and Application of Marine Equipment, the Key laboratory of Ship Intelligent System and Technologies, the Key laboratory of Environment Intelligent Perception, the College of Intelligent System Science and Engineering, Harbin Engineering University, 145 Nantong Street, Harbin, 150001, China.

概括

本研究介绍了注意力增强对比学习 (AECL) 用于短文本集群,有效地解决了虚假负分离问题. AECL产生了歧视性表示,大大提高了对现有方法的集群性能.