@inproceedings{wang2022promda,
author = {Wang, Yufei and Xu, Can and Sun, Qingfeng and Hu, Huang and Tao, Chongyang and Geng, Xiubo and Jiang (姜大昕), Daxin},
title = {PromDA: Prompt-based Data Augmentation for Low-Resource NLU Tasks},
booktitle = {ACL 2022},
year = {2022},
month = {February},
abstract = {This paper focuses on the Data Augmentation for low-resource Natural Language Understanding (NLU) tasks. We propose Prompt-based D]ata Augmentation model (PromDA) which only trains small-scale Soft Prompt (i.e., a set of trainable vectors) in the frozen Pre-trained Language Models (PLMs). This avoids human effort in collecting unlabeled in-domain data and maintains the quality of generated synthetic data. In addition, PromDA generates synthetic data via two different views and filters out the low-quality data using NLU models. Experiments on four benchmarks show that synthetic data produced by PromDA successfully boost up the performance of NLU models which consistently outperform several competitive baseline models, including a state-of-the-art semi-supervised model using unlabeled in-domain data. The synthetic data from PromDA are also complementary with unlabeled in-domain data. The NLU models can be further improved when they are combined for training.},
url = {http://approjects.co.za/?big=en-us/research/publication/promda-prompt-based-data-augmentation-for-low-resource-nlu-tasks/},
}