princeton-nlp / LM-BFF

[ACL 2021] LM-BFF: Better Few-shot Fine-tuning of Language Models https://arxiv.org/abs/2012.15723

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Table 3 uses manual label words or generated label words?

wjczf123 opened this issue · comments

I notice that the automatic selection of label words does not always achieve a good performance. So the results of Table 1 use manual label words?

Hi,

Results in Table 3 use either manual template+manual label words (manual) or auto template+manual label words (auto).