NAACL 2022long20 citations
SUBS: Subtree Substitution for Compositional Semantic Parsing
Jingfeng Yang, Le Zhang, Diyi Yang
Abstract
Although sequence-to-sequence models often achieve good performance in semantic parsing for i.i.d. data, their performance is still inferior in compositional generalization. Several data augmentation methods have been proposed to alleviate this problem. However, prior work only leveraged superficial grammar or rules for data augmentation, which resulted in limited improvement. We propose to use subtree substitution for compositional data augmentation, where we consider subtrees with similar semantic functions as exchangeable. Our experiments showed that such augmented data led to significantly better performance on Scan and GeoQuery, and reached new SOTA on compositional split of GeoQuery.
BibTeX
@inproceedings{yang-etal-2022-subs,
title = "{SUBS}: Subtree Substitution for Compositional Semantic Parsing",
author = "Yang, Jingfeng and
Zhang, Le and
Yang, Diyi",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.12/",
doi = "10.18653/v1/2022.naacl-main.12",
pages = "169--174"
}