MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers 论文

2021引用 233
DOIPDF
Topic ModelingNatural Language Processing TechniquesMultimodal Machine Learning Applications
人工智能Natural Language Processing TechniquesTopic ModelingMultimodal Machine Learning Applications
相关技术:Natural Language Processing TechniquesTopic ModelingMultimodal Machine Learning Applications
关系图谱

MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers · 相关事件

暂无数据