Recent works have shown promising results of prompt tuning in stimulating pre-trained language models (PLMs) for natural language processing (NLP) tasks. However, to the best of our knowledge, existing works focus on prompt-tuning generative PLMs that are pre-trained to generate target tokens, such as BERT. It is still unknown whether and how discriminative PLMs, e.g., ELECTRA, can be effectively prompt-tuned. In this work, we present DPT, the first prompt tuning framework for discriminative PLMs, which reformulates NLP tasks into a discriminative language modeling problem. Comprehensive experiments on text classification and question answering show that, compared with vanilla fine-tuning, DPT achieves significantly higher performance, and also prevents the unstable problem in tuning large PLMs in both full-set and low-resource settings. The source code and experiment details of this paper can be obtained from https://github.com/thunlp/DPT.
@article{arxiv.2205.11166,
title = {Prompt Tuning for Discriminative Pre-trained Language Models},
author = {Yuan Yao and Bowen Dong and Ao Zhang and Zhengyan Zhang and Ruobing Xie and Zhiyuan Liu and Leyu Lin and Maosong Sun and Jianyong Wang},
journal= {arXiv preprint arXiv:2205.11166},
year = {2022}
}