English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Multi-text applications, such as multi-document summarization, are typicallyrequired to model redundancies across related texts. Current methodsconfronting consolidation struggle to fuse overlapping information. In order toexplicitly represent content overlap, we propose to align predicate-argumentrelations across texts, providing a potential scaffold for informationconsolidation. We go beyond clustering coreferring mentions, and instead modeloverlap with respect to redundancy at a propositional level, rather than merelydetecting shared referents. Our setting exploits QA-SRL, utilizingquestion-answer pairs to capture predicate-argument relations, facilitatinglaymen annotation of cross-text alignments. We employ crowd-workers forconstructing a dataset of QA-based alignments, and present a baseline QAalignment model trained over our dataset. Analyses show that our new task issemantically challenging, capturing content overlap beyond lexical similarityand complements cross-document coreference with proposition-level links,offering potential use for downstream tasks.

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