We introduce HATELEXICON, a lexicon of slurs and targets of hate speech for Brazil, Germany, India and Kenya, to aid model development and interpretability. First, we demonstrate how HATELEXICON can be used to interpret model predictions, showing that models developed to classify extreme speech rely heavily on target group names. Further, we propose a culturally-informed method to aid shot selection for training in low-resource settings. In few-shot learning, shot selection is of paramount importance to model performance and we need to ensure we make the most of available data. We work with HASOC German and Hindi data for training and the Multilingual HateCheck (MHC) benchmark for evaluation. We show that selecting shots based on our lexicon leads to models performing better than models trained on shots sampled randomly. Thus, when given only a few training examples, using HATELEXICON to select shots containing more sociocultural information leads to better few-shot performance. With these two use-cases we show how our HATELEXICON can be used for more effective hate speech detection.

In industry settings, machine learning is an attractive tool to automatize processes. Unfortunately, annotated and high-quality data is expensive to source. This problem is exacerbated in settings spanning multiple markets and languages. Thus, developing solutions for multilingual tasks with little available data is challenging. Few-shot learning is a compelling approach when building solutions in multilingual and low-resource settings, since the method not only requires just a few training examples to achieve high performance, but is also a technique agnostic to language. Even though the technique can be applied to multilingual settings, optimizing performance is an open question. In our work we show that leveraging higher-resource, task-specific language data can boost overall performance and we propose a method to select training examples per their average performance in a Monte Carlo simulation, resulting in a training set more conducive to learning. We demonstrate the effectiveness of our methods in fashion text reviews moderation, classifying reviews as related or unrelated to the given product. We show that our methodology boosts performance in multilingual (English, French, German) settings, increasing F1 score and significantly decreasing false positives.

To tackle the rising phenomenon of hate speech, efforts have been made towards data curation and analysis. When it comes to analysis of bias, previous work has focused predominantly on race. In our work, we further investigate bias in hate speech datasets along racial, gender and intersectional axes. We identify strong bias against African American English (AAE), masculine and AAE+Masculine tweets, which are annotated as disproportionately more hateful and offensive than from other demographics. We provide evidence that BERT-based models propagate this bias and show that balancing the training data for these protected attributes can lead to fairer models with regards to gender, but not race.

Research to tackle hate speech plaguing online media has made strides in providing solutions, analyzing bias and curating data. A challenging problem is ambiguity between hate speech and offensive language, causing low performance both overall and specifically for the hate speech class. It can be argued that misclassifying actual hate speech content as merely offensive can lead to further harm against targeted groups. In our work, we mitigate this potentially harmful phenomenon by proposing an adversarial debiasing method to separate the two classes. We show that our method works for English, Arabic German and Hindi, plus in a multilingual setting, improving performance over baselines.

Building on current work on multilingual hate speech (e.g., Ousidhoum et al. (2019)) and hate speech reduction (e.g., Sap et al. (2020)), we present XTREMESPEECH, a new hate speech dataset containing 20,297 social media passages from Brazil, Germany, India and Kenya. The key novelty is that we directly involve the affected communities in collecting and annotating the data – as opposed to giving companies and governments control over defining and combatting hate speech. This inclusive approach results in datasets more representative of actually occurring online speech and is likely to facilitate the removal of the social media content that marginalized communities view as causing the most harm. Based on XTREMESPEECH, we establish novel tasks with accompanying baselines, provide evidence that cross-country training is generally not feasible due to cultural differences between countries and perform an interpretability analysis of BERT’s predictions.

False information spread via the internet and social media influences public opinion and user activity, while generative models enable fake content to be generated faster and more cheaply than had previously been possible. In the not so distant future, identifying fake content generated by deep learning models will play a key role in protecting users from misinformation. To this end, a dataset containing human and computer-generated headlines was created and a user study indicated that humans were only able to identify the fake headlines in 47.8% of the cases. However, the most accurate automatic approach, transformers, achieved an overall accuracy of 85.7%, indicating that content generated from language models can be filtered out accurately.

In previous work, it has been shown that BERT can adequately align cross-lingual sentences on the word level. Here we investigate whether BERT can also operate as a char-level aligner. The languages examined are English, Fake English, German and Greek. We show that the closer two languages are, the better BERT can align them on the character level. BERT indeed works well in English to Fake English alignment, but this does not generalize to natural languages to the same extent. Nevertheless, the proximity of two languages does seem to be a factor. English is more related to German than to Greek and this is reflected in how well BERT aligns them; English to German is better than English to Greek. We examine multiple setups and show that the similarity matrices for natural languages show weaker relations the further apart two languages are.

When tackling a task in a given domain, it has been shown that adapting a model to the domain using raw text data before training on the supervised task improves performance versus solely training on the task. The downside is that a lot of domain data is required and if we want to tackle tasks in n domains, we require n models each adapted on domain data before task learning. Storing and using these models separately can be prohibitive for low-end devices. In this paper we show that domain adaptation can be generalised to cover multiple domains. Specifically, a single model can be trained across various domains at the same time with minimal drop in performance, even when we use less data and resources. Thus, instead of training multiple models, we can train a single multidomain model saving on computational resources and training time.

The size of the vocabulary is a central design choice in large pretrained language models, with respect to both performance and memory requirements. Typically, subword tokenization algorithms such as byte pair encoding and WordPiece are used. In this work, we investigate the compatibility of tokenizations for multilingual static and contextualized embedding spaces and propose a measure that reflects the compatibility of tokenizations across languages. Our goal is to prevent incompatible tokenizations, e.g., “wine” (word-level) in English vs. “v i n” (character-level) in French, which make it hard to learn good multilingual semantic representations. We show that our compatibility measure allows the system designer to create vocabularies across languages that are compatible – a desideratum that so far has been neglected in multilingual models.

Parody is a figurative device used to imitate an entity for comedic or critical purposes and represents a widespread phenomenon in social media through many popular parody accounts. In this paper, we present the first computational study of parody. We introduce a new publicly available data set of tweets from real politicians and their corresponding parody accounts. We run a battery of supervised machine learning models for automatically detecting parody tweets with an emphasis on robustness by testing on tweets from accounts unseen in training, across different genders and across countries. Our results show that political parody tweets can be predicted with an accuracy up to 90%. Finally, we identify the markers of parody through a linguistic analysis. Beyond research in linguistics and political communication, accurately and automatically detecting parody is important to improving fact checking for journalists and analytics such as sentiment analysis through filtering out parodical utterances.