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

A corpus of vector-embedded text documents has some empirical distribution.Given two corpora, we want to calculate a single metric of distance (e.g.,Mauve, Frechet Inception) between them. We describe an abstract quality, called`distributionality', of such metrics. A non-distributional metric tends to usevery local measurements, or uses global measurements in a way that does notfully reflect the distributions' true distance. For example, if individualpairwise nearest-neighbor distances are low, it may judge the two corpora tohave low distance, even if their two distributions are in fact far from eachother. A more distributional metric will, in contrast, better capture thedistributions' overall distance. We quantify this quality by constructing aKnown-Similarity Corpora set from two paraphrase corpora and calculating thedistance between paired corpora from it. The distances' trend shape as setelement separation increases should quantify the distributionality of themetric. We propose that Average Hausdorff Distance and energy distance betweencorpora are representative examples of non-distributional and distributionaldistance metrics, to which other metrics can be compared, to evaluate howdistributional they are.

Characterizing how 'distributional' NLP corpora distance metrics are