most citedDon't Judge a Language Model by Its Last Layer: Contrastive Learning with Layer-Wise Attention Pooling

5 citations · 5 across the 1 of their papers we have counts for

collaborators

1 paper

cs.CL2022★ 5 cited

Don't Judge a Language Model by Its Last Layer: Contrastive Learning with Layer-Wise Attention Pooling

Dongsuk Oh, Yejin Kim, Hodong Lee +2

Recent pre-trained language models (PLMs) achieved great success on many natural language processing tasks through learning linguistic features and contextualized sentence represen…