Discriminative Language Model as Semantic Consistency Scorer for Prompt-based Few-Shot Text Classification

no code implementations • 23 Oct 2022 • Zhipeng Xie, Yahe Li

This paper proposes a novel prompt-based finetuning method (called DLM-SCS) for few-shot text classification by utilizing the discriminative language model ELECTRA that is pretrained to distinguish whether a token is original or generated.

Few-Shot Text Classification Language Modelling +1