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

Recent works have widely adopted large language model pretraining for sourcecode, suggested source code-specific pretraining objectives and investigatedthe applicability of various Transformer-based language model architectures forsource code. This work investigates another important aspect of such models,namely the effect of different subtokenization options, and aims at identifyingmost effective and length-efficient subtokenizations, taking into account codespecifics. We propose subtokenziation that reduces average length by 17%without downstream performance drop, and show that a carefully chosensubtokenization may improve quality by 0.5-2%, possibly with some lengthincrease.

CodeBPE: Investigating Subtokenization Options for Large Language Model Pretraining on Source Code