Discriminative Language Model as Semantic Consistency Scorer for Prompt-based Few-Shot Text Classification
This is an incremental improvement for few-shot text classification tasks, enhancing prompt-based methods with a novel scoring approach.
The paper tackles few-shot text classification by proposing DLM-SCS, a prompt-based finetuning method that uses ELECTRA to score semantic consistency, achieving state-of-the-art performance in experiments.
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. The underlying idea is that the prompt instantiated with the true label should have higher semantic consistency score than other prompts with false labels. Since a prompt usually consists of several components (or parts), its semantic consistency can be decomposed accordingly. The semantic consistency of each component is then computed by making use of the pretrained ELECTRA model, without introducing extra parameters. Extensive experiments have shown that our model outperforms several state-of-the-art prompt-based few-shot methods.