arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.04313cs.CV
收藏

野生模因:评估仇恨模因挑战数据集的普遍性

Memes in the Wild: Assessing the Generalizability of the Hateful Memes Challenge Dataset

Oxford Internet Institute(牛津互联网研究院);Dept. of Computer Science(计算机科学系);Oxford Uehiro Centre for Practical Ethics(牛津上广实践伦理中心);Dept. of Engineering Science(工程科学系)

Hannah Rose Kirk, Yennie Jun, Paulius Rauba, Gal Wachtel, Ruining Li, Xingjian Bai, Noah Broestl, Martin Doff-Sotta, Aleksandar Shtedritski, Yuki M. Asano

摘要:

仇恨模因对当前的机器学习系统提出了独特的挑战,因为它们的信息来自文本和视觉模态。为此,Facebook发布了“仇恨迷因挑战”,这是一个带有预先提取的文本标题的迷因数据集,但目前还不清楚这些合成的例子是否可以推广到“野生迷因”。在本文中,我们从Pinterest中收集了仇恨和非仇恨的模因,以评估在Facebook数据集上预训练的模型的样本外性能。我们发现,在野外的模因在两个关键方面不同:1)字幕必须通过OCR提取,注入噪声和降低多模态模型的性能,2)模因比“传统模因”更多样化,包括对话或文本的屏幕截图在一个简单的背景。因此,本文作为一个现实检查仇恨模因检测和检测现实世界的仇恨其适用性的当前基准。

英文摘要:

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 text captions, but it is unclear whether these synthetic examples generalize to `memes in the wild'. In this paper, we collect hateful and non-hateful memes from Pinterest to evaluate out-of-sample performance on models pre-trained on the Facebook dataset. We find that memes in the wild differ in two key aspects: 1) Captions must be extracted via OCR, injecting noise and diminishing performance of multimodal models, and 2) Memes are more diverse than `traditional memes', including screenshots of conversations or text on a plain background. This paper thus serves as a reality check for the current benchmark of hateful meme detection and its applicability for detecting real world hate.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑