Label-Aware Automatic Verbalizer for Few-Shot Text Classification

TL;DR

This paper introduces LAAV, an automatic verbalizer that enhances prompt-based few-shot text classification by generating more effective class-representative words, outperforming manual methods across multiple languages.

Contribution

The paper proposes LAAV, a novel automatic verbalizer that augments manual labels with conjunctions to improve few-shot classification performance.

Findings

LAAV significantly outperforms existing verbalizers on five datasets.

LAAV generates more relevant words, especially in low-resource languages.

Experimental results confirm the effectiveness of LAAV across multiple languages.

Abstract

Prompt-based learning has shown its effectiveness in few-shot text classification. One important factor in its success is a verbalizer, which translates output from a language model into a predicted class. Notably, the simplest and widely acknowledged verbalizer employs manual labels to represent the classes. However, manual selection does not guarantee the optimality of the selected words when conditioned on the chosen language model. Therefore, we propose Label-Aware Automatic Verbalizer (LAAV), effectively augmenting the manual labels to achieve better few-shot classification results. Specifically, we use the manual labels along with the conjunction "and" to induce the model to generate more effective words for the verbalizer. The experimental results on five datasets across five languages demonstrate that LAAV significantly outperforms existing verbalizers. Furthermore, our analysis reveals that LAAV suggests more relevant words compared to similar approaches, especially in mid-to-low resource languages.