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

Alban Petit, Caio Filippo Corro, François Yvon

Submission Type: Regular Long Paper

Submission Track: Syntax, Parsing and their Applications

Submission Track 2: Semantics: Lexical, Sentence level, Document Level, Textual Inference, etc.

Keywords: semantic parsing, compositional generalization, graph-based parsing

TL;DR: We extend a graph-based semantic parser with a supertagging step for compositional generalization.

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 parsing framework in several ways to alleviate this issue, notably:
(1) the introduction of a supertagging step with valency constraints, expressed as an integer linear program;
(2) the 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, these results confirm that structural constraints are important for generalization in semantic parsing.

Submission Number: 3030