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

Traditional text classification approaches often require a good amount oflabeled data, which is difficult to obtain, especially in restricted domains orless widespread languages. This lack of labeled data has led to the rise oflow-resource methods, that assume low data availability in natural languageprocessing. Among them, zero-shot learning stands out, which consists oflearning a classifier without any previously labeled data. The best resultsreported with this approach use language models such as Transformers, but fallinto two problems: high execution time and inability to handle long texts asinput. This paper proposes a new model, ZeroBERTo, which leverages anunsupervised clustering step to obtain a compressed data representation beforethe classification task. We show that ZeroBERTo has better performance for longinputs and shorter execution time, outperforming XLM-R by about 12% in the F1score in the FolhaUOL dataset. Keywords: Low-Resource NLP, Unlabeled data,Zero-Shot Learning, Topic Modeling, Transformers.

ZeroBERTo: Leveraging Zero-Shot Text Classification by Topic Modeling