Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned 论文

2019引用 1048
DOIArXivPDF
Natural Language Processing TechniquesTopic ModelingSoftware Engineering Research
企业软件Natural Language Processing TechniquesTopic ModelingSoftware Engineering Research
相关技术:Topic ModelingNatural Language Processing Techniques
关系图谱

Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned · 相关文章

暂无数据