QA-Noun: Representing Nominal Semantics via Natural Language Question-Answer Pairs

TL;DR

QA-Noun introduces a novel QA-based framework for capturing noun-centered semantics, enhancing fine-grained sentence decomposition and complementing existing predicate-focused approaches for improved semantic alignment.

Contribution

It presents nine question templates for noun semantics, a new dataset, and a trained model that together improve the coverage and granularity of semantic decomposition.

Findings

Achieves near-complete coverage of AMR's noun arguments.

Surfaces additional contextually implied relations.

Over 130% higher granularity than recent methods.

Abstract

Decomposing sentences into fine-grained meaning units is increasingly used to model semantic alignment. While QA-based semantic approaches have shown effectiveness for representing predicate-argument relations, they have so far left noun-centered semantics largely unaddressed. We introduce QA-Noun, a QA-based framework for capturing noun-centered semantic relations. QA-Noun defines nine question templates that cover both explicit syntactical and implicit contextual roles for nouns, producing interpretable QA pairs that complement verbal QA-SRL. We release detailed guidelines, a dataset of over 2,000 annotated noun mentions, and a trained model integrated with QA-SRL to yield a unified decomposition of sentence meaning into individual, highly fine-grained, facts. Evaluation shows that QA-Noun achieves near-complete coverage of AMR's noun arguments while surfacing additional contextually implied relations, and that combining QA-Noun with QA-SRL yields over 130\% higher granularity than recent fact-based decomposition methods such as FactScore and DecompScore. QA-Noun thus complements the broader QA-based semantic framework, forming a comprehensive and scalable approach to fine-grained semantic decomposition for cross-text alignment.