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

TL;DR

This paper introduces DLM-SCS, a prompt-based few-shot text classification method that uses ELECTRA as a semantic consistency scorer, effectively distinguishing true labels from false ones without extra parameters.

Contribution

The paper presents a novel approach leveraging ELECTRA's discriminative capabilities to assess semantic consistency in prompts, improving few-shot classification performance.

Findings

Outperforms several state-of-the-art prompt-based few-shot methods

Utilizes ELECTRA without adding extra parameters

Effectively measures semantic consistency for label verification

Abstract

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.