Improving Compositional Generalization with Latent Structure and Data Augmentation

Linlu Qiu, Peter Shaw, Panupong Pasupat, Pawel Nowak, Tal Linzen, Fei Sha, Kristina Toutanova


Abstract
Generic unstructured neural networks have been shown to struggle on out-of-distribution compositional generalization. Compositional data augmentation via example recombination has transferred some prior knowledge about compositionality to such black-box neural models for several semantic parsing tasks, but this often required task-specific engineering or provided limited gains. We present a more powerful data recombination method using a model called Compositional Structure Learner (CSL). CSL is a generative model with a quasi-synchronous context-free grammar backbone, which we induce from the training data. We sample recombined examples from CSL and add them to the fine-tuning data of a pre-trained sequence-to-sequence model (T5). This procedure effectively transfers most of CSL’s compositional bias to T5 for diagnostic tasks, and results in a model even stronger than a T5-CSL ensemble on two real world compositional generalization tasks. This results in new state-of-the-art performance for these challenging semantic parsing tasks requiring generalization to both natural language variation and novel compositions of elements.
Anthology ID:
2022.naacl-main.323
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
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4341–4362
Language:
URL:
https://aclanthology.org/2022.naacl-main.323
DOI:
10.18653/v1/2022.naacl-main.323
Bibkey:
Cite (ACL):
Linlu Qiu, Peter Shaw, Panupong Pasupat, Pawel Nowak, Tal Linzen, Fei Sha, and Kristina Toutanova. 2022. Improving Compositional Generalization with Latent Structure and Data Augmentation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4341–4362, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Improving Compositional Generalization with Latent Structure and Data Augmentation (Qiu et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.323.pdf
Code
 google-research/language
Data
C4SCAN