Abstract
We propose a novel graph-based approach for semantic parsing that resolves two problems observed in the literature: (1) seq2seq models fail on compositional generalization tasks; (2) previous work using phrase structure parsers cannot cover all the semantic parses observed in treebanks. We prove that both MAP inference and latent tag anchoring (required for weakly-supervised learning) are NP-hard problems. We propose two optimization algorithms based on constraint smoothing and conditional gradient to approximately solve these inference problems. Experimentally, our approach delivers state-of-the-art results on GeoQuery, Scan, and Clevr, both for i.i.d. splits and for splits that test for compositional generalization.- Anthology ID:
- 2023.tacl-1.41
- Volume:
- Transactions of the Association for Computational Linguistics, Volume 11
- Month:
- Year:
- 2023
- Address:
- Cambridge, MA
- Venue:
- TACL
- SIG:
- Publisher:
- MIT Press
- Note:
- Pages:
- 703–722
- Language:
- URL:
- https://aclanthology.org/2023.tacl-1.41
- DOI:
- 10.1162/tacl_a_00570
- Cite (ACL):
- Alban Petit and Caio Corro. 2023. On Graph-based Reentrancy-free Semantic Parsing. Transactions of the Association for Computational Linguistics, 11:703–722.
- Cite (Informal):
- On Graph-based Reentrancy-free Semantic Parsing (Petit & Corro, TACL 2023)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/2023.tacl-1.41.pdf