[HN Gopher] Hierarchical transformers are more efficient languag... ___________________________________________________________________ Hierarchical transformers are more efficient language models Author : beefman Score : 13 points Date : 2021-11-04 21:56 UTC (1 hours ago) (HTM) web link (arxiv.org) (TXT) w3m dump (arxiv.org) ___________________________________________________________________ (page generated 2021-11-04 23:00 UTC)