logseq/pages/hls__ase2023-jf-paper98_1687870120885_0.md

file:: ase2023-jf-paper98_1687870120885_0.pdf file-path:: ../assets/ase2023-jf-paper98_1687870120885_0.pdf

• PLMs are pre-trained on large natural language corpora, they have learned knowledge that can be transferred for other tasks and domains in zero-shot (i.e., no labeled data is available) or few shot settings (i.e., only a few labeled data is available for training). ls-type:: annotation hl-page:: 1 hl-color:: green id:: 649b115b-e89d-4add-b821-2e319d8ef437