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

Interactive programming with interleaved code snippet cells and naturallanguage markdown is recently gaining popularity in the form of Jupyternotebooks, which accelerate prototyping and collaboration. To study codegeneration conditioned on a long context history, we present JuICe, a corpus of1.5 million examples with a curated test set of 3.7K instances based on onlineprogramming assignments. Compared with existing contextual code generationdatasets, JuICe provides refined human-curated data, open-domain code, and anorder of magnitude more training data. Using JuICe, we train models for twotasks: (1) generation of the API call sequence in a code cell, and (2) fullcode cell generation, both conditioned on the NL-Code history up to aparticular code cell. Experiments using current baseline code generation modelsshow that both context and distant supervision aid in generation, and that thedataset is challenging for current systems.

JuICe: A Large Scale Distantly Supervised Dataset for Open Domain Context-based Code Generation