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

This paper describes a novel study on using `Attention Mask' input intransformers and using this approach for detecting offensive content in bothEnglish and Persian languages. The paper's principal focus is to suggest amethodology to enhance the performance of the BERT-based models on the`Offensive Language Detection' task. Therefore, we customize attentionprobabilities by changing the `Attention Mask' input to create more efficaciousword embeddings. To do this, we firstly tokenize the training set of theexploited datasets (by BERT tokenizer). Then, we apply Multinomial Naive Bayesto map these tokens to two probabilities. These probabilities indicate thelikelihood of making a text non-offensive or offensive, provided that itcontains that token. Afterwards, we use these probabilities to define a newterm, namely Offensive Score. Next, we create two separate (because of thedifferences in the types of the employed datasets) equations based on OffensiveScores for each language to re-distribute the `Attention Mask' input for payingmore attention to more offensive phrases. Eventually, we put the F1-macro scoreas our evaluation metric and fine-tune several combinations of BERT with ANNs,CNNs and RNNs to examine the effect of using this methodology on variouscombinations. The results indicate that all models will enhance with thismethodology. The most improvement was 2% and 10% for English and Persianlanguages, respectively.

Offensive Language Detection with BERT-based models, By Customizing Attention Probabilities