Open AccessPosted Content
The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes
Douwe Kiela,Hamed Firooz,Aravind Mohan,Vedanuj Goswami,Amanpreet Singh,Pratik Ringshia,Davide Testuggine +6 more
TLDR
The authors proposed a new challenge set for multimodal classification, focusing on detecting hate speech in multi-modal memes, where difficult examples are added to the dataset to make it hard to rely on unimodal signals.Abstract:
This work proposes a new challenge set for multimodal classification, focusing on detecting hate speech in multimodal memes. It is constructed such that unimodal models struggle and only multimodal models can succeed: difficult examples ("benign confounders") are added to the dataset to make it hard to rely on unimodal signals. The task requires subtle reasoning, yet is straightforward to evaluate as a binary classification problem. We provide baseline performance numbers for unimodal models, as well as for multimodal models with various degrees of sophistication. We find that state-of-the-art methods perform poorly compared to humans (64.73% vs. 84.7% accuracy), illustrating the difficulty of the task and highlighting the challenge that this important problem poses to the community.read more
Citations
More filters
Posted Content
Learning Transferable Visual Models From Natural Language Supervision
Alec Radford,Jong Wook Kim,Chris Hallacy,Aditya Ramesh,Gabriel Goh,Sandhini Agarwal,Girish Sastry,Amanda Askell,Pamela Mishkin,Jack Clark,Gretchen Krueger,Ilya Sutskever +11 more
TL;DR: In this article, a pre-training task of predicting which caption goes with which image is used to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet.
Proceedings ArticleDOI
Overview of the HASOC track at FIRE 2019: Hate Speech and Offensive Content Identification in Indo-European Languages
Thomas Mandl,Sandip Modha,Prasenjit Majumder,Daksh Patel,Mohana Dave,Chintak Mandlia,Aditya Patel +6 more
TL;DR: The HASOC track intends to stimulate development in Hate Speech for Hindi, German and English by identifying Hate Speech in Social Media using LSTM networks processing word embedding input.
Journal ArticleDOI
Directions in abusive language training data, a systematic review: Garbage in, garbage out.
Bertie Vidgen,Leon Derczynski +1 more
TL;DR: This paper systematically reviews abusive language dataset creation and content in conjunction with an open website for cataloguing abusive language data leading to a synthesis providing evidence-based recommendations for practitioners working with this complex and highly diverse data.
Proceedings ArticleDOI
TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text
TL;DR: TextOCR as discussed by the authors is an arbitrary-shaped scene text detection and recognition with 900k annotated words collected on real images from TextVQA dataset, which can do scene text based reasoning on an image in an end-to-end fashion.
Posted Content
Tackling Online Abuse: A Survey of Automated Abuse Detection Methods
TL;DR: A comprehensive survey of the methods that have been proposed to date for automated abuse detection in the field of natural language processing (NLP), providing a platform for further development of this area.
References
More filters
Proceedings ArticleDOI
Multimodal news article analysis
TL;DR: This paper presents a series of tasks and baseline approaches to leverage corpus such as the BreakingNews dataset and highlights online news articles as a potential next step for this area of research.
Posted Content
Interpretable Multi-Modal Hate Speech Detection.
TL;DR: This article proposed a deep neural multi-modal model that can detect hate speech by effectively capturing the semantics of the text along with socio-cultural context in which a particular hate expression is made, and provide interpretable insights into decisions of the model.