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

In recent years, multilingual pre-trained language models have gainedprominence due to their remarkable performance on numerous downstream NaturalLanguage Processing tasks (NLP). However, pre-training these large multilinguallanguage models requires a lot of training data, which is not available forAfrican Languages. Active learning is a semi-supervised learning algorithm, inwhich a model consistently and dynamically learns to identify the mostbeneficial samples to train itself on, in order to achieve better optimizationand performance on downstream tasks. Furthermore, active learning effectivelyand practically addresses real-world data scarcity. Despite all its benefits,active learning, in the context of NLP and especially multilingual languagemodels pretraining, has received little consideration. In this paper, wepresent AfroLM, a multilingual language model pretrained from scratch on 23African languages (the largest effort to date) using our novel self-activelearning framework. Pretrained on a dataset significantly (14x) smaller thanexisting baselines, AfroLM outperforms many multilingual pretrained languagemodels (AfriBERTa, XLMR-base, mBERT) on various NLP downstream tasks (NER, textclassification, and sentiment analysis). Additional out-of-domain sentimentanalysis experiments show that \textbf{AfroLM} is able to generalize wellacross various domains. We release the code source, and our datasets used inour framework at https://github.com/bonaventuredossou/MLM_AL.

AfroLM: A Self-Active Learning-based Multilingual Pretrained Language Model for 23 African Languages