On graph-based reentrancy-free semantic parsing

TL;DR

This paper introduces a graph-based semantic parsing method that overcomes limitations of seq2seq models and phrase structure parsers, achieving state-of-the-art results on multiple datasets, including challenging compositional generalization tasks.

Contribution

It presents a novel graph-based approach with new optimization algorithms for inference, addressing NP-hard problems in semantic parsing.

Findings

State-of-the-art results on Geoquery, Scan, and Clevr datasets.

Effective handling of compositional generalization tasks.

Proven NP-hardness of MAP inference and latent tag anchoring.

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.