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

Automated evaluation of text generation systems has recently seen increasingattention, particularly checking whether generated text stays truthful to inputsources. Existing methods frequently rely on an evaluation using task-specificlanguage models, which in turn allows for little interpretability of generatedscores. We introduce SRLScore, a reference-free evaluation metric designed withtext summarization in mind. Our approach generates fact tuples constructed fromSemantic Role Labels, applied to both input and summary texts. A finalfactuality score is computed by an adjustable scoring mechanism, which allowsfor easy adaption of the method across domains. Correlation with humanjudgments on English summarization datasets shows that SRLScore is competitivewith state-of-the-art methods and exhibits stable generalization acrossdatasets without requiring further training or hyperparameter tuning. Weexperiment with an optional co-reference resolution step, but find that theperformance boost is mostly outweighed by the additional compute required. Ourmetric is available online at https://github.com/heyjing/SRLScore.

Evaluating Factual Consistency of Texts with Semantic Role Labeling