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

While recent work on automated fact-checking has focused mainly on verifyingand explaining claims, for which the list of claims is readily available,identifying check-worthy claim sentences from a text remains challenging.Current claim identification models rely on manual annotations for eachsentence in the text, which is an expensive task and challenging to conduct ona frequent basis across multiple domains. This paper explores methodology toidentify check-worthy claim sentences from fake news articles, irrespective ofdomain, without explicit sentence-level annotations. We leverage two internalsupervisory signals - headline and the abstractive summary - to rank thesentences based on semantic similarity. We hypothesize that this rankingdirectly correlates to the check-worthiness of the sentences. To assess theeffectiveness of this hypothesis, we build pipelines that leverage the rankingof sentences based on either the headline or the abstractive summary. Thetop-ranked sentences are used for the downstream fact-checking tasks ofevidence retrieval and the article's veracity prediction by the pipeline. Ourfindings suggest that the top 3 ranked sentences contain enough information forevidence-based fact-checking of a fake news article. We also show that whilethe headline has more gisting similarity with how a fact-checking websitewrites a claim, the summary-based pipeline is the most promising for anend-to-end fact-checking system.

Assessing Effectiveness of Using Internal Signals for Check-Worthy Claim Identification in Unlabeled Data for Automated Fact-Checking