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

Mining large corpora can generate useful discoveries but is time-consumingfor humans. We formulate a new task, D5, that automatically discoversdifferences between two large corpora in a goal-driven way. The task input is aproblem comprising a research goal "$\textit{comparing the side effects of drugA and drug B}$" and a corpus pair (two large collections of patients'self-reported reactions after taking each drug). The output is a languagedescription (discovery) of how these corpora differ (patients taking drug A"$\textit{mention feelings of paranoia}$" more often). We build a D5 system,and to quantitatively measure its performance, we 1) contribute a meta-dataset,OpenD5, aggregating 675 open-ended problems ranging across business, socialsciences, humanities, machine learning, and health, and 2) propose a set ofunified evaluation metrics: validity, relevance, novelty, and significance.With the dataset and the unified metrics, we confirm that language models canuse the goals to propose more relevant, novel, and significant candidatediscoveries. Finally, our system produces discoveries previously unknown to theauthors on a wide range of applications in OpenD5, including temporal anddemographic differences in discussion topics, political stances and stereotypesin speech, insights in commercial reviews, and error patterns in NLP models.

Goal Driven Discovery of Distributional Differences via Language Descriptions