@inproceedings{wang2021want,
author = {Wang, Shuohang and Liu, Yang and Xu, Yichong and Zhu, Chenguang and Zeng, Michael},
title = {Want To Reduce Labeling Cost? GPT-3 Can Help},
booktitle = {Conference on Empirical Methods in Natural Language Processing},
year = {2021},
month = {August},
abstract = {Data annotation is a time-consuming and labor-intensive process for many NLP tasks. Although there exist various methods to produce pseudo data labels, they are often task-specific and require a decent amount of labeled data to start with. Recently, the immense language model GPT-3 with 175 billion parameters has achieved tremendous improvement across many few-shot learning tasks. In this paper, we explore ways to leverage GPT-3 as a low-cost data labeler to train other models. We find that, to make the downstream model achieve the same performance on a variety of NLU and NLG tasks, it costs 50% to 96% less to use labels from GPT-3 than using labels from humans. Furthermore, we propose a novel framework of combining pseudo labels from GPT-3 with human labels, which leads to even better performance with limited labeling budget. These results present a cost-effective data labeling methodology that is generalizable to many practical applications.},
url = {http://approjects.co.za/?big=en-us/research/publication/want-to-reduce-labeling-cost-gpt-3-can-help/},
}