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

This paper describes the solutions submitted by the UPB team to theAuTexTification shared task, featured as part of IberLEF-2023. Our teamparticipated in the first subtask, identifying text documents produced by largelanguage models instead of humans. The organizers provided a bilingual datasetfor this subtask, comprising English and Spanish texts covering multipledomains, such as legal texts, social media posts, and how-to articles. Weexperimented mostly with deep learning models based on Transformers, as well astraining techniques such as multi-task learning and virtual adversarialtraining to obtain better results. We submitted three runs, two of whichconsisted of ensemble models. Our best-performing model achieved macroF1-scores of 66.63% on the English dataset and 67.10% on the Spanish dataset.

UPB at IberLEF-2023 AuTexTification: Detection of Machine-Generated Text using Transformer Ensembles