PSSAT: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Filling
Guanting Dong, Daichi Guo, Liwen Wang, Xuefeng Li, Zechen Wang, Chen Zeng, Keqing He, Jinzheng Zhao
Abstract
Most existing slot filling models tend to memorize inherent patterns of entities and corresponding contexts from training data. However, these models can lead to system failure or undesirable outputs when being exposed to spoken language perturbation or variation in practice. We propose a perturbed semantic structure awareness transferring method for training perturbation-robust slot filling models. Specifically, we introduce two MLM-based training strategies to respectively learn contextual semantic structure and word distribution from unsupervised language perturbation corpus. Then, we transfer semantic knowledge learned from upstream training procedure into the original samples and filter generated data by consistency processing. These procedures aims to enhance the robustness of slot filling models. Experimental results show that our method consistently outperforms the previous basic methods and gains strong generalization while preventing the model from memorizing inherent patterns of entities and contexts.
BibTeX
@inproceedings{dong-etal-2022-pssat,
title = "{PSSAT}: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Filling",
author = "Dong, Guanting and
Guo, Daichi and
Wang, Liwen and
Li, Xuefeng and
Wang, Zechen and
Zeng, Chen and
He, Keqing and
Zhao, Jinzheng and
Lei, Hao and
Cui, Xinyue and
Huang, Yi and
Feng, Junlan and
Xu, Weiran",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.473/",
pages = "5327--5334"
}