CLLGFeb 15, 2023

On graph-based reentrancy-free semantic parsing

arXiv:2302.07679v1223 citationsh-index: 3
Originality Highly original
AI Analysis

This addresses semantic parsing challenges for natural language processing applications, offering a novel solution to improve generalization and coverage.

The paper tackles the problems of seq2seq models failing on compositional generalization tasks and phrase structure parsers not covering all semantic parses, proposing a graph-based approach that achieves state-of-the-art results on Geoquery, Scan, and Clevr datasets for both i.i.d. and compositional generalization splits.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes