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

How do two distributions of texts differ? Humans are slow at answering this,since discovering patterns might require tediously reading through hundreds ofsamples. We propose to automatically summarize the differences by "learning anatural language hypothesis": given two distributions $D_{0}$ and $D_{1}$, wesearch for a description that is more often true for $D_{1}$, e.g., "ismilitary-related." To tackle this problem, we fine-tune GPT-3 to proposedescriptions with the prompt: "[samples of $D_{0}$] + [samples of $D_{1}$] +the difference between them is." We then re-rank the descriptions bychecking how often they hold on a larger set of samples with a learnedverifier. On a benchmark of 54 real-world binary classification tasks, whileGPT-3 Curie (13B) only generates a description similar to human annotation 7%of the time, the performance reaches 61% with fine-tuning and re-ranking, andour best system using GPT-3 Davinci (175B) reaches 76%. We apply our system todescribe distribution shifts, debug dataset shortcuts, summarize unknown tasks,and label text clusters, and present analyses based on automatically generateddescriptions.

Describing Differences between Text Distributions with Natural Language