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

Maintaining factual consistency is a critical issue in abstractive textsummarisation, however, it cannot be assessed by traditional automatic metricsused for evaluating text summarisation, such as ROUGE scoring. Recent effortshave been devoted to developing improved metrics for measuring factualconsistency using pre-trained language models, but these metrics haverestrictive token limits, and are therefore not suitable for evaluating longdocument text summarisation. Moreover, there is limited research evaluatingwhether existing automatic evaluation metrics are fit for purpose when appliedto long document data sets. In this work, we evaluate the efficacy of automaticmetrics at assessing factual consistency in long document text summarisationand propose a new evaluation framework LongDocFACTScore. This framework allowsmetrics to be extended to any length document. This framework outperformsexisting state-of-the-art metrics in its ability to correlate with humanmeasures of factuality when used to evaluate long document summarisation datasets. Furthermore, we show LongDocFACTScore has performance comparable tostate-of-the-art metrics when evaluated against human measures of factualconsistency on short document data sets. We make our code and annotated datapublicly available: https://github.com/jbshp/LongDocFACTScore.

LongDocFACTScore: Evaluating the Factuality of Long Document Abstractive Summarisation