SPE: Symmetrical Prompt Enhancement for Fact Probing
Yiyuan Li, Tong Che, Yezhen Wang, Zhengbao Jiang, Caiming Xiong, Snigdha Chaturvedi
Abstract
Pretrained language models (PLMs) have been shown to accumulate factual knowledge during pretraining (Petroni et al. 2019). Recent works probe PLMs for the extent of this knowledge through prompts either in discrete or continuous forms. However, these methods do not consider symmetry of the task: object prediction and subject prediction. In this work, we propose Symmetrical Prompt Enhancement (SPE), a continuous prompt-based method for factual probing in PLMs that leverages the symmetry of the task by constructing symmetrical prompts for subject and object prediction. Our results on a popular factual probing dataset, LAMA, show significant improvement of SPE over previous probing methods.
BibTeX
@inproceedings{li-etal-2022-spe,
title = "{SPE}: Symmetrical Prompt Enhancement for Fact Probing",
author = "Li, Yiyuan and
Che, Tong and
Wang, Yezhen and
Jiang, Zhengbao and
Xiong, Caiming and
Chaturvedi, Snigdha",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.803/",
doi = "10.18653/v1/2022.emnlp-main.803",
pages = "11689--11698"
}