Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge

Velioglu R, Rose J (2020)
In: arXiv:2012.12975.

Konferenzbeitrag | Veröffentlicht | Englisch
 
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Velioglu, RizaUniBi ; Rose, Jewgeni
Abstract / Bemerkung
Memes on the Internet are often harmless and sometimes amusing. However, by using certain types of images, text, or combinations of both, the seemingly harmless meme becomes a multimodal type of hate speech -- a hateful meme. The Hateful Memes Challenge is a first-of-its-kind competition which focuses on detecting hate speech in multimodal memes and it proposes a new data set containing 10,000+ new examples of multimodal content. We utilize VisualBERT -- which meant to be the BERT of vision and language -- that was trained multimodally on images and captions and apply Ensemble Learning. Our approach achieves 0.811 AUROC with an accuracy of 0.765 on the challenge test set and placed third out of 3,173 participants in the Hateful Memes Challenge.
Erscheinungsjahr
2020
Titel des Konferenzbandes
arXiv:2012.12975
Konferenz
NeurIPS
Konferenzort
Virtual
Konferenzdatum
2020-12-06 – 2020-12-12
Page URI
https://pub.uni-bielefeld.de/record/2965471

Zitieren

Velioglu R, Rose J. Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge. In: arXiv:2012.12975. 2020.
Velioglu, R., & Rose, J. (2020). Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge. arXiv:2012.12975
Velioglu, Riza, and Rose, Jewgeni. 2020. “Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge”. In arXiv:2012.12975.
Velioglu, R., and Rose, J. (2020). “Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge” in arXiv:2012.12975.
Velioglu, R., & Rose, J., 2020. Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge. In arXiv:2012.12975.
R. Velioglu and J. Rose, “Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge”, arXiv:2012.12975, 2020.
Velioglu, R., Rose, J.: Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge. arXiv:2012.12975. (2020).
Velioglu, Riza, and Rose, Jewgeni. “Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge”. arXiv:2012.12975. 2020.
Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Quellen

arXiv: 2012.12975

Suchen in

Google Scholar