QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositions
This addresses the challenge of information consolidation in tasks like multi-document summarization, though it appears incremental as it builds on existing QA-SRL methods.
The paper tackles the problem of modeling content overlap across texts for multi-text applications by aligning predicate-argument relations at a propositional level, resulting in a new dataset and baseline model that captures semantic overlap beyond lexical similarity.
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.