Label-Aware Automatic Verbalizer for Few-Shot Text Classification

Anonymous

TL;DR: We propose Label-Aware Automatic Verbalizer (LAAV), leveraging class labels to construct a reliable verbalizer for prompt-based few-shot text classification.

Abstract: Prompt-based learning has shown its effectiveness in few-shot text classification. A key 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 utilize the label name 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, ranging from low-resource to high-resource, demonstrate that LAAV significantly outperforms existing verbalizers.

Paper Type: short

Research Area: Efficient/Low-Resource Methods for NLP

Contribution Types: NLP engineering experiment, Approaches to low-resource settings

Languages Studied: English, Indonesian, Tagalog, Thai, Vietnamese