Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification

TL;DR

This paper introduces Knowledgeable Prompt-tuning (KPT), which enhances prompt-based text classification by integrating external knowledge into the verbalizer, leading to more stable and effective performance especially in low-data scenarios.

Contribution

The paper proposes a novel method to incorporate external knowledge into verbalizers for prompt-tuning, improving coverage and reducing bias in text classification tasks.

Findings

KPT outperforms baseline prompt-tuning methods in zero and few-shot settings.

Incorporating external knowledge improves verbalizer coverage and stability.

Extensive experiments validate the effectiveness of KPT.

Abstract

Tuning pre-trained language models (PLMs) with task-specific prompts has been a promising approach for text classification. Particularly, previous studies suggest that prompt-tuning has remarkable superiority in the low-data scenario over the generic fine-tuning methods with extra classifiers. The core idea of prompt-tuning is to insert text pieces, i.e., template, to the input and transform a classification problem into a masked language modeling problem, where a crucial step is to construct a projection, i.e., verbalizer, between a label space and a label word space. A verbalizer is usually handcrafted or searched by gradient descent, which may lack coverage and bring considerable bias and high variances to the results. In this work, we focus on incorporating external knowledge into the verbalizer, forming a knowledgeable prompt-tuning (KPT), to improve and stabilize prompt-tuning. Specifically, we expand the label word space of the verbalizer using external knowledge bases (KBs) and refine the expanded label word space with the PLM itself before predicting with the expanded label word space. Extensive experiments on zero and few-shot text classification tasks demonstrate the effectiveness of knowledgeable prompt-tuning.