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

With the growth of social media platform influence, the effect of theirmisuse becomes more and more impactful. The importance of automatic detectionof threatening and abusive language can not be overestimated. However, most ofthe existing studies and state-of-the-art methods focus on English as thetarget language, with limited work on low- and medium-resource languages. Inthis paper, we present two shared tasks of abusive and threatening languagedetection for the Urdu language which has more than 170 million speakersworldwide. Both are posed as binary classification tasks where participatingsystems are required to classify tweets in Urdu into two classes, namely: (i)Abusive and Non-Abusive for the first task, and (ii) Threatening andNon-Threatening for the second. We present two manually annotated datasetscontaining tweets labelled as (i) Abusive and Non-Abusive, and (ii) Threateningand Non-Threatening. The abusive dataset contains 2400 annotated tweets in thetrain part and 1100 annotated tweets in the test part. The threatening datasetcontains 6000 annotated tweets in the train part and 3950 annotated tweets inthe test part. We also provide logistic regression and BERT-based baselineclassifiers for both tasks. In this shared task, 21 teams from six countriesregistered for participation (India, Pakistan, China, Malaysia, United ArabEmirates, and Taiwan), 10 teams submitted their runs for Subtask A, which isAbusive Language Detection and 9 teams submitted their runs for Subtask B,which is Threatening Language detection, and seven teams submitted theirtechnical reports. The best performing system achieved an F1-score value of0.880 for Subtask A and 0.545 for Subtask B. For both subtasks, m-Bert basedtransformer model showed the best performance.

Overview of Abusive and Threatening Language Detection in Urdu at FIRE 2021