Abstract
We show how the AM parser, a compositional semantic parser (Groschwitz et al., 2018) can solve compositional generalization on the COGS dataset. It is the first semantic parser that achieves high accuracy on both naturally occurring language and the synthetic COGS dataset. We discuss implications for corpus and model design for learning human-like generalization. Our results suggest that compositional generalization can be best achieved by building compositionality into semantic parsers.- Anthology ID:
- 2022.starsem-1.4
- Volume:
- Proceedings of the 11th Joint Conference on Lexical and Computational Semantics
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, Washington
- Editors:
- Vivi Nastase, Ellie Pavlick, Mohammad Taher Pilehvar, Jose Camacho-Collados, Alessandro Raganato
- Venue:
- *SEM
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 44–54
- Language:
- URL:
- https://aclanthology.org/2022.starsem-1.4
- DOI:
- 10.18653/v1/2022.starsem-1.4
- Cite (ACL):
- Pia Weißenhorn, Lucia Donatelli, and Alexander Koller. 2022. Compositional generalization with a broad-coverage semantic parser. In Proceedings of the 11th Joint Conference on Lexical and Computational Semantics, pages 44–54, Seattle, Washington. Association for Computational Linguistics.
- Cite (Informal):
- Compositional generalization with a broad-coverage semantic parser (Weißenhorn et al., *SEM 2022)
- PDF:
- https://preview.aclanthology.org/ingest-bitext-workshop/2022.starsem-1.4.pdf
- Code
- coli-saar/am-parser
- Data
- CFQ, SCAN