English

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

Computation and Language 2021-09-28 v1

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.

Keywords

Cite

@article{arxiv.2109.12655,
  title  = {QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositions},
  author = {Daniela Brook Weiss and Paul Roit and Ayal Klein and Ori Ernst and Ido Dagan},
  journal= {arXiv preprint arXiv:2109.12655},
  year   = {2021}
}

Comments

Accepted to EMNLP 2021, Main Conference

R2 v1 2026-06-24T06:20:47.457Z