Improving Compositional Generalization in Semantic Parsing
Inbar Oren, Jonathan Herzig, Nitish Gupta, Matt Gardner, Jonathan Berant
Abstract
Generalization of models to out-of-distribution (OOD) data has captured tremendous attention recently. Specifically, compositional generalization, i.e., whether a model generalizes to new structures built of components observed during training, has sparked substantial interest. In this work, we investigate compositional generalization in semantic parsing, a natural test-bed for compositional generalization, as output programs are constructed from sub-components. We analyze a wide variety of models and propose multiple extensions to the attention module of the semantic parser, aiming to improve compositional generalization. We find that the following factors improve compositional generalization: (a) using contextual representations, such as ELMo and BERT, (b) informing the decoder what input tokens have previously been attended to, (c) training the decoder attention to agree with pre-computed token alignments, and (d) downsampling examples corresponding to frequent program templates. While we substantially reduce the gap between in-distribution and OOD generalization, performance on OOD compositions is still substantially lower.- Anthology ID:
- 2020.findings-emnlp.225
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2020
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Trevor Cohn, Yulan He, Yang Liu
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2482–2495
- Language:
- URL:
- https://aclanthology.org/2020.findings-emnlp.225
- DOI:
- 10.18653/v1/2020.findings-emnlp.225
- Cite (ACL):
- Inbar Oren, Jonathan Herzig, Nitish Gupta, Matt Gardner, and Jonathan Berant. 2020. Improving Compositional Generalization in Semantic Parsing. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2482–2495, Online. Association for Computational Linguistics.
- Cite (Informal):
- Improving Compositional Generalization in Semantic Parsing (Oren et al., Findings 2020)
- PDF:
- https://preview.aclanthology.org/revert-3132-ingestion-checklist/2020.findings-emnlp.225.pdf
- Code
- inbaroren/improving-compgen-in-semparse
- Data
- DROP, SCAN