QA-Noun: Representing Nominal Semantics via Natural Language Question-Answer Pairs
This work addresses the need for fine-grained semantic decomposition in natural language processing, particularly for cross-text alignment, though it is incremental as it extends existing QA-based frameworks to nouns.
The paper tackles the problem of representing noun-centered semantic relations in sentences, which had been unaddressed by existing QA-based approaches, by introducing QA-Noun, a framework that uses question templates to produce interpretable QA pairs, achieving near-complete coverage of AMR's noun arguments and over 130% higher granularity when combined with QA-SRL compared to recent methods.
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.