Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?

Peter Shaw, Ming-Wei Chang, Panupong Pasupat, Kristina Toutanova


Abstract
Sequence-to-sequence models excel at handling natural language variation, but have been shown to struggle with out-of-distribution compositional generalization. This has motivated new specialized architectures with stronger compositional biases, but most of these approaches have only been evaluated on synthetically-generated datasets, which are not representative of natural language variation. In this work we ask: can we develop a semantic parsing approach that handles both natural language variation and compositional generalization? To better assess this capability, we propose new train and test splits of non-synthetic datasets. We demonstrate that strong existing approaches do not perform well across a broad set of evaluations. We also propose NQG-T5, a hybrid model that combines a high-precision grammar-based approach with a pre-trained sequence-to-sequence model. It outperforms existing approaches across several compositional generalization challenges on non-synthetic data, while also being competitive with the state-of-the-art on standard evaluations. While still far from solving this problem, our study highlights the importance of diverse evaluations and the open challenge of handling both compositional generalization and natural language variation in semantic parsing.
Anthology ID:
2021.acl-long.75
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
922–938
Language:
URL:
https://aclanthology.org/2021.acl-long.75
DOI:
10.18653/v1/2021.acl-long.75
Bibkey:
Cite (ACL):
Peter Shaw, Ming-Wei Chang, Panupong Pasupat, and Kristina Toutanova. 2021. Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 922–938, Online. Association for Computational Linguistics.
Cite (Informal):
Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both? (Shaw et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.75.pdf
Video:
 https://aclanthology.org/2021.acl-long.75.mp4
Code
 google-research/language
Data
CFQSCAN