QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositions

TL;DR

This paper introduces QA-Align, a novel method for representing cross-text content overlap by aligning predicate-argument relations using QA-SRL, which improves redundancy modeling in multi-text applications.

Contribution

It proposes a new QA-based alignment approach for cross-text content overlap, including a dataset and baseline model, advancing beyond coreference clustering.

Findings

QA-Align captures semantic overlap beyond lexical similarity.

The dataset enables training and evaluating QA alignment models.

Proposition-level alignment complements coreference for better redundancy modeling.

Abstract

Multi-text applications, such as multi-document summarization, are typically required to model redundancies across related texts. Current methods confronting consolidation struggle to fuse overlapping information. In order to explicitly represent content overlap, we propose to align predicate-argument relations across texts, providing a potential scaffold for information consolidation. We go beyond clustering coreferring mentions, and instead model overlap with respect to redundancy at a propositional level, rather than merely detecting shared referents. Our setting exploits QA-SRL, utilizing question-answer pairs to capture predicate-argument relations, facilitating laymen annotation of cross-text alignments. We employ crowd-workers for constructing a dataset of QA-based alignments, and present a baseline QA alignment model trained over our dataset. Analyses show that our new task is semantically challenging, capturing content overlap beyond lexical similarity and complements cross-document coreference with proposition-level links, offering potential use for downstream tasks.