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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Multi-document summarization is a challenging task due to its inherentsubjective bias, highlighted by the low inter-annotator ROUGE-1 score of 0.4among DUC-2004 reference summaries. In this work, we aim to enhance theobjectivity of news summarization by focusing on the main event of a group ofrelated news documents and presenting it coherently with sufficient context.Our primary objective is to succinctly report the main event, ensuring that thesummary remains objective and informative. To achieve this, we employ anextract-rewrite approach that incorporates a main-event biasedmonotone-submodular function for content selection. This enables us to extractthe most crucial information related to the main event from the documentcluster. To ensure coherence, we utilize a fine-tuned Language Model (LLM) forrewriting the extracted content into a coherent text. The evaluation usingobjective metrics and human evaluators confirms the effectiveness of ourapproach, as it surpasses potential baselines, demonstrating excellence in bothcontent coverage, coherence, and informativeness.

LLM Based Multi-Document Summarization Exploiting Main-Event Biased Monotone Submodular Content Extraction