vix.ing · top · new · best · stats · spec

Structural generalization in COGS: Supertagging is (almost) all you need

2023/10/21 by Alban Petit, Petit, Alban, Caio Corro +3
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2310.14124

openalex publication_date 2023/10/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In many Natural Language Processing applications, neural networks have been found to fail to generalize on out-of-distribution examples. In particular, several recent semantic parsing datasets have put forward important limitations of neural networks in cases where compositional generalization is required. In this work, we extend a neural graph-based semantic parsing framework in several ways to alleviate this issue. Notably, we propose: (1) the introduction of a supertagging step with valency constraints, expressed as an integer linear program; (2) a reduction of the graph prediction problem to the maximum matching problem; (3) the design of an incremental early-stopping training strategy to prevent overfitting. Experimentally, our approach significantly improves results on examples that require structural generalization in the COGS dataset, a known challenging benchmark for compositional generalization. Overall, our results confirm that structural constraints are important for generalization in semantic parsing.

Related