MetricPrompt: Prompting Model as a Relevance Metric for Few-shot Text Classification
This work addresses a key bottleneck in few-shot text classification for NLP practitioners, offering an incremental improvement over existing methods.
The paper tackles the difficulty of designing verbalizers in prompting models for few-shot text classification by proposing MetricPrompt, which reformulates the task as text pair relevance estimation, and it achieves new state-of-the-art performance across three datasets and four few-shot settings.
Prompting methods have shown impressive performance in a variety of text mining tasks and applications, especially few-shot ones. Despite the promising prospects, the performance of prompting model largely depends on the design of prompt template and verbalizer. In this work, we propose MetricPrompt, which eases verbalizer design difficulty by reformulating few-shot text classification task into text pair relevance estimation task. MetricPrompt adopts prompting model as the relevance metric, further bridging the gap between Pre-trained Language Model's (PLM) pre-training objective and text classification task, making possible PLM's smooth adaption. Taking a training sample and a query one simultaneously, MetricPrompt captures cross-sample relevance information for accurate relevance estimation. We conduct experiments on three widely used text classification datasets across four few-shot settings. Results show that MetricPrompt outperforms manual verbalizer and other automatic verbalizer design methods across all few-shot settings, achieving new state-of-the-art (SOTA) performance.