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.- Anthology ID:
- 2022.naacl-main.12
- Volume:
- Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Editors:
- Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 169–174
- Language:
- URL:
- https://aclanthology.org/2022.naacl-main.12
- DOI:
- 10.18653/v1/2022.naacl-main.12
- Cite (ACL):
- Jingfeng Yang, Le Zhang, and Diyi Yang. 2022. SUBS: Subtree Substitution for Compositional Semantic Parsing. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 169–174, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- SUBS: Subtree Substitution for Compositional Semantic Parsing (Yang et al., NAACL 2022)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2022.naacl-main.12.pdf
- Code
- gt-salt/subs