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

In recent times, the detection of hate-speech, offensive, or abusive languagein online media has become an important topic in NLP research due to theexponential growth of social media and the propagation of such messages, aswell as their impact. Misogyny detection, even though it plays an importantpart in hate-speech detection, has not received the same attention. In thispaper, we describe our classification systems submitted to the SemEval-2022Task 5: MAMI - Multimedia Automatic Misogyny Identification. The shared taskaimed to identify misogynous content in a multi-modal setting by analysing memeimages together with their textual captions. To this end, we propose two modelsbased on the pre-trained UNITER model, one enhanced with an image sentimentclassifier, whereas the second leverages a Vocabulary Graph ConvolutionalNetwork (VGCN). Additionally, we explore an ensemble using the aforementionedmodels. Our best model reaches an F1-score of 71.4% in Sub-task A and 67.3% forSub-task B positioning our team in the upper third of the leaderboard. Werelease the code and experiments for our models on GitHub

UPB at SemEval-2022 Task 5: Enhancing UNITER with Image Sentiment and Graph Convolutional Networks for Multimedia Automatic Misogyny Identification