Label-Aware Automatic Verbalizer for Few-Shot Text Classification
This work addresses the bottleneck of manual verbalizer design in few-shot learning, offering an incremental improvement for researchers and practitioners in NLP.
The paper tackles the suboptimal manual label selection in prompt-based few-shot text classification by proposing LAAV, which augments manual labels with generated words to improve classification, achieving significant performance gains across five datasets and languages.
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.