On Graph-based Reentrancy-free Semantic Parsing - Traitement du Langage Parlé
Journal Articles Transactions of the Association for Computational Linguistics Year : 2023

On Graph-based Reentrancy-free Semantic Parsing

Alban Petit
  • Function : Author
  • PersonId : 1144131
Caio Corro

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.
Fichier principal
Vignette du fichier
2023.tacl-1.41.pdf (484.35 Ko) Télécharger le fichier
Origin Publisher files allowed on an open archive

Dates and versions

hal-04189119 , version 1 (28-08-2023)

Identifiers

Cite

Alban Petit, Caio Corro. On Graph-based Reentrancy-free Semantic Parsing. Transactions of the Association for Computational Linguistics, 2023, 11, pp.703-722. ⟨10.1162/tacl_a_00570⟩. ⟨hal-04189119⟩
175 View
46 Download

Altmetric

Share

More