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

African languages are severely under-represented in NLP research due to lackof datasets covering several NLP tasks. While there are individual languagespecific datasets that are being expanded to different tasks, only a handful ofNLP tasks (e.g. named entity recognition and machine translation) havestandardized benchmark datasets covering several geographical andtypologically-diverse African languages. In this paper, we develop MasakhaNEWS-- a new benchmark dataset for news topic classification covering 16 languageswidely spoken in Africa. We provide an evaluation of baseline models bytraining classical machine learning models and fine-tuning several languagemodels. Furthermore, we explore several alternatives to full fine-tuning oflanguage models that are better suited for zero-shot and few-shot learning suchas cross-lingual parameter-efficient fine-tuning (like MAD-X), patternexploiting training (PET), prompting language models (like ChatGPT), andprompt-free sentence transformer fine-tuning (SetFit and Cohere Embedding API).Our evaluation in zero-shot setting shows the potential of prompting ChatGPTfor news topic classification in low-resource African languages, achieving anaverage performance of 70 F1 points without leveraging additional supervisionlike MAD-X. In few-shot setting, we show that with as little as 10 examples perlabel, we achieved more than 90\% (i.e. 86.0 F1 points) of the performance offull supervised training (92.6 F1 points) leveraging the PET approach.

MasakhaNEWS: News Topic Classification for African languages