STPrompt: Semantic-guided and Task-driven prompts for Effective Few-shot Classification

TL;DR

STPrompt introduces semantic-guided, task-driven prompts for few-shot classification, automatically selecting effective prompts from semantic cues, leading to state-of-the-art results across multiple datasets.

Contribution

The paper proposes a novel semantic-guided prompt construction method that automatically selects prompts based on semantic dependency and task metadata, improving few-shot classification.

Findings

Achieves state-of-the-art performance on five datasets.

Demonstrates the effectiveness of semantic prompts in knowledge probing.

Shows automatic prompt selection enhances few-shot learning.

Abstract

The effectiveness of prompt learning has been demonstrated in different pre-trained language models. By formulating suitable template and choosing representative label mapping, prompt learning can be used as an efficient knowledge probe. However, finding suitable prompt in existing methods requires multiple experimental attempts or appropriate vector initialization on formulating suitable template and choosing representative label mapping, which it is more common in few-shot learning tasks. Motivating by PLM working process, we try to construct the prompt from task semantic perspective and thus propose the STPrompt -Semantic-guided and Task-driven Prompt model. Specifically, two novel prompts generated from the semantic dependency tree (Dep-prompt) and task-specific metadata description (Meta-prompt), are firstly constructed in a prompt augmented pool, and the proposed model would automatically select a suitable semantic prompt to motivating the prompt learning process. Our results show that the proposed model achieves the state-of-the-art performance in five different datasets of few-shot text classification tasks, which prove that more semantic and significant prompts could assume as a better knowledge proving tool.