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

Evaluating the quality of generated text is difficult, since traditional NLGevaluation metrics, focusing more on surface form than meaning, often fail toassign appropriate scores. This is especially problematic for AMR-to-textevaluation, given the abstract nature of AMR. Our work aims to support thedevelopment and improvement of NLG evaluation metrics that focus on meaning, bydeveloping a dynamic CheckList for NLG metrics that is interpreted by beingorganized around meaning-relevant linguistic phenomena. Each test instanceconsists of a pair of sentences with their AMR graphs and a human-producedtextual semantic similarity or relatedness score. Our CheckList facilitatescomparative evaluation of metrics and reveals strengths and weaknesses of noveland traditional metrics. We demonstrate the usefulness of CheckList bydesigning a new metric GraCo that computes lexical cohesion graphs over AMRconcepts. Our analysis suggests that GraCo presents an interesting NLG metricworth future investigation and that meaning-oriented NLG metrics can profitfrom graph-based metric components using AMR.

A Dynamic, Interpreted CheckList for Meaning-oriented NLG Metric Evaluation -- through the Lens of Semantic Similarity Rating