Even though hate speech (HS) online has been an important object of research in the last decade, most HS-related corpora over-simplify the phenomenon of hate by attempting to label user comments as “hate” or “neutral”. This ignores the complex and subjective nature of HS, which limits the real-life applicability of classifiers trained on these corpora. In this study, we present the M-Phasis corpus, a corpus of ~9k German and French user comments collected from migration-related news articles. It goes beyond the “hate”-“neutral” dichotomy and is instead annotated with 23 features, which in combination become descriptors of various types of speech, ranging from critical comments to implicit and explicit expressions of hate. The annotations are performed by 4 native speakers per language and achieve high (0.77 <= k <= 1) inter-annotator agreements. Besides describing the corpus creation and presenting insights from a content, error and domain analysis, we explore its data characteristics by training several classification baselines.

Recent research on style transfer takes inspiration from unsupervised neural machine translation (UNMT), learning from large amounts of non-parallel data by exploiting cycle consistency loss, back-translation, and denoising autoencoders. By contrast, the use of selfsupervised NMT (SSNMT), which leverages (near) parallel instances hidden in non-parallel data more efficiently than UNMT, has not yet been explored for style transfer. In this paper we present a novel Self-Supervised Style Transfer (3ST) model, which augments SSNMT with UNMT methods in order to identify and efficiently exploit supervisory signals in non-parallel social media posts. We compare 3ST with state-of-the-art (SOTA) style transfer models across civil rephrasing, formality and polarity tasks. We show that 3ST is able to balance the three major objectives (fluency, content preservation, attribute transfer accuracy) the best, outperforming SOTA models on averaged performance across their tested tasks in automatic and human evaluation.

Hate speech and profanity detection suffer from data sparsity, especially for languages other than English, due to the subjective nature of the tasks and the resulting annotation incompatibility of existing corpora. In this study, we identify profane subspaces in word and sentence representations and explore their generalization capability on a variety of similar and distant target tasks in a zero-shot setting. This is done monolingually (German) and cross-lingually to closely-related (English), distantly-related (French) and non-related (Arabic) tasks. We observe that, on both similar and distant target tasks and across all languages, the subspace-based representations transfer more effectively than standard BERT representations in the zero-shot setting, with improvements between F1 +10.9 and F1 +42.9 over the baselines across all tested monolingual and cross-lingual scenarios.

Documents as short as a single sentence may inadvertently reveal sensitive information about their authors, including e.g. their gender or ethnicity. Style transfer is an effective way of transforming texts in order to remove any information that enables author profiling. However, for a number of current state-of-the-art approaches the improved privacy is accompanied by an undesirable drop in the down-stream utility of the transformed data. In this paper, we propose a simple, zero-shot way to effectively lower the risk of author profiling through multilingual back-translation using off-the-shelf translation models. We compare our models with five representative text style transfer models on three datasets across different domains. Results from both an automatic and a human evaluation show that our approach achieves the best overall performance while requiring no training data. We are able to lower the adversarial prediction of gender and race by up to 22% while retaining 95% of the original utility on downstream tasks.

We discuss the impact of data bias on abusive language detection. We show that classification scores on popular datasets reported in previous work are much lower under realistic settings in which this bias is reduced. Such biases are most notably observed on datasets that are created by focused sampling instead of random sampling. Datasets with a higher proportion of implicit abuse are more affected than datasets with a lower proportion.