Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Guanhuan Huang"'
Publikováno v:
ACL/IJCNLP (Findings)
The major paradigm of applying a pre-trained language model to downstream tasks is to fine-tune it on labeled task data, which often suffers instability and low performance when the labeled examples are scarce.~One way to alleviate this problem is to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::de72811421f2a927e0ec67b78bb19796
http://arxiv.org/abs/2106.02327
http://arxiv.org/abs/2106.02327
