الميمات هي مجموعات من النص والصور التي غالبا ما تكون روح الدعابة في الطبيعة.ولكن، قد لا يكون هذا هو الحال دائما، وقد تصور مجموعات معينة من النصوص والصور الكراهية، يشار إليها باسم الميمات البغيضة.يقدم هذا العمل خط أنابيب متعدد الوسائط يأخذ كل من الميزات المرئية والنصية من الميمات إلى (1) تحديد الفئة المحمية (على سبيل المثال، الجنس، الجنس وما إلى ذلك) التي هاجمت؛و (2) اكتشاف نوع الهجوم (E.G. ازدراء، Slurs وما إلى ذلك).يستخدم خط أنابيبنا تمثيلا مرئيا ومرئيا تدريبا مسبقا مسبقا، متبوعا بتصنيف الانحدار اللوجستي البسيط.نحن نوظف خط أنابيبنا على مجموعة بيانات تحدي الميمات البغيضة مع ملصقات إضافية تم إنشاؤها حديثا عن الفئة المحمية ونوع الهجوم.يحقق أفضل نموذج لدينا AUROC من 0.96 لتحديد الفئة المحمية، و 0.97 للكشف عن نوع الهجوم.نطلق سرد علاماتنا في https://github.com/harisbinzia/hatefulmemes
Memes are the combinations of text and images that are often humorous in nature. But, that may not always be the case, and certain combinations of texts and images may depict hate, referred to as hateful memes. This work presents a multimodal pipeline that takes both visual and textual features from memes into account to (1) identify the protected category (e.g. race, sex etc.) that has been attacked; and (2) detect the type of attack (e.g. contempt, slurs etc.). Our pipeline uses state-of-the-art pre-trained visual and textual representations, followed by a simple logistic regression classifier. We employ our pipeline on the Hateful Memes Challenge dataset with additional newly created fine-grained labels for protected category and type of attack. Our best model achieves an AUROC of 0.96 for identifying the protected category, and 0.97 for detecting the type of attack. We release our code at https://github.com/harisbinzia/HatefulMemes
References used
https://aclanthology.org/
The Shared Task on Hateful Memes is a challenge that aims at the detection of hateful content in memes by inviting the implementation of systems that understand memes, potentially by combining image and textual information. The challenge consists of
Hateful memes pose a unique challenge for current machine learning systems because their message is derived from both text- and visual-modalities. To this effect, Facebook released the Hateful Memes Challenge, a dataset of memes with pre-extracted te
This paper describes our submission (winning solution for Task A) to the Shared Task on Hateful Meme Detection at WOAH 2021. We build our system on top of a state-of-the-art system for binary hateful meme classification that already uses image tags s
We present the results and main findings of the shared task at WOAH 5 on hateful memes detection. The task include two subtasks relating to distinct challenges in the fine-grained detection of hateful memes: (1) the protected category attacked by the
An abundance of methodological work aims to detect hateful and racist language in text. However, these tools are hampered by problems like low annotator agreement and remain largely disconnected from theoretical work on race and racism in the social