Combating the hate speech in Thai textual memes

Abstract

Thai textual memes have been popular in social media, as a form of image information summarization. Unfortunately, many memes contain some hateful content that easily causes the controversy in Thailand. For global protection, the Hateful Memes Challenge is also provided by Facebook AI to enable researchers to compete their algorithms for combating the hate speech on memes as one of NeurIPS’20 competitions. As well as in Thailand, this paper introduces the Thai textual meme detection as a new research problem in Thai natural language processing (Thai-NLP) that is the settlement of transmission linkage between scene text localization, Thai optical recognition (Thai-OCR) and language understanding. From the results, both regular and irregular text position can be localized by one-stage detection pipeline. More scene text can be augmented by different resolution and rotation. The accuracy of Thai-OCR using convolutional neural network (CNN) can be improved by recurrent neural network (RNN). Since misspelling Thai words are frequently used in social, this paper categorizes them as synonyms to train on multi-task pre-trained language model.