What Does BERT Look At? An Analysis of BERT’s Attention 论文总结

文章目录 往期文章链接目录 Before we start Surface-Level Patterns in Attention Probing Individual Attention Heads Probing Attention Head Combinations Clustering Attention Heads 往期文章链接目录 往期文章链接目录 Before we start In

>>阅读原文<<