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

Large language models (e.g., GPT-4) are uniquely capable of producing highlyrated text simplification, yet current human evaluation methods fail to providea clear understanding of systems' specific strengths and weaknesses. To addressthis limitation, we introduce SALSA, an edit-based human annotation frameworkthat enables holistic and fine-grained text simplification evaluation. Wedevelop twenty one linguistically grounded edit types, covering the fullspectrum of success and failure across dimensions of conceptual, syntactic andlexical simplicity. Using SALSA, we collect 19K edit annotations on 840simplifications, revealing discrepancies in the distribution of simplificationstrategies performed by fine-tuned models, prompted LLMs and humans, and findGPT-3.5 performs more quality edits than humans, but still exhibits frequenterrors. Using our fine-grained annotations, we develop LENS-SALSA, areference-free automatic simplification metric, trained to predict sentence-and word-level quality simultaneously. Additionally, we introduce word-levelquality estimation for simplification and report promising baseline results.Our data, new metric, and annotation toolkit are available athttps://salsa-eval.com.

Dancing Between Success and Failure: Edit-level Simplification Evaluation using SALSA