Recent years pretrained language models (PLMs) hit a success on several downstream tasks, showing their power on modeling language. To better understand and leverage what PLMs have learned, several techniques have emerged to explore syntactic structures entailed by PLMs. However, few efforts have been made to explore grounding capabilities of PLMs, which are also essential. In this paper, we highlight the ability of PLMs to discover which token should be grounded to which concept, if combined with our proposed erasing-then-awakening approach. Empirical studies on four datasets demonstrate that our approach can awaken latent grounding which is understandable to human experts, even if it is not exposed to such labels during training. More importantly, our approach shows great potential to benefit downstream semantic parsing models. Taking text-to-SQL as a case study, we successfully couple our approach with two off-the-shelf parsers, obtaining an absolute improvement of up to 9.8%.
@article{arxiv.2109.10540,
title = {Awakening Latent Grounding from Pretrained Language Models for Semantic Parsing},
author = {Qian Liu and Dejian Yang and Jiahui Zhang and Jiaqi Guo and Bin Zhou and Jian-Guang Lou},
journal= {arXiv preprint arXiv:2109.10540},
year = {2021}
}
Comments
Accepted by ACL 2021 Findings. The first three authors contributed equally