相关论文: No offence, Bert -- I insult only humans! Multiple…

The spectacular expansion of the Internet has led to the development of a new research problem in the field of natural language processing: automatic toxic comment detection, since many countries prohibit hate speech in public media. There…

With the spread of social networks and their unfortunate use for hate speech, automatic detection of the latter has become a pressing problem. In this paper, we reproduce seven state-of-the-art hate speech detection models from prior work,…

The problem of online offensive language limits the health and security of online users. It is essential to apply the latest state-of-the-art techniques in developing a system to detect online offensive language and to ensure social justice…

Toxic online speech has become a crucial problem nowadays due to an exponential increase in the use of internet by people from different cultures and educational backgrounds. Differentiating if a text message belongs to hate speech and…

Social media and online forums are increasingly becoming popular. Unfortunately, these platforms are being used for spreading hate speech. In this paper, we design black-box techniques to protect users from hate-speech on online platforms…

Neural machine translation systems are known to be vulnerable to adversarial test inputs, however, as we show in this paper, these systems are also vulnerable to training attacks. Specifically, we propose a poisoning attack in which a…

Machine learning based language models have recently made significant progress, which introduces a danger to spread misinformation. To combat this potential danger, several methods have been proposed for detecting text written by these…

Explainable AI is a strong strategy implemented to understand complex black-box model predictions in a human interpretable language. It provides the evidence required to execute the use of trustworthy and reliable AI systems. On the other…

Robustness of huge Transformer-based models for natural language processing is an important issue due to their capabilities and wide adoption. One way to understand and improve robustness of these models is an exploration of an adversarial…

Detecting and classifying instances of hate in social media text has been a problem of interest in Natural Language Processing in the recent years. Our work leverages state of the art Transformer language models to identify hate speech in a…

The proliferation of social media platforms has led to an increase in the spread of hate speech, particularly targeting vulnerable communities. Unfortunately, existing methods for automatically identifying and blocking toxic language rely…

While in real life everyone behaves themselves at least to some extent, it is much more difficult to expect people to behave themselves on the internet, because there are few checks or consequences for posting something toxic to others.…

In recent years, the introduction of the Transformer models sparked a revolution in natural language processing (NLP). BERT was one of the first text encoders using only the attention mechanism without any recurrent parts to achieve…

Hate speech, offensive language, aggression, racism, sexism, and other abusive language are common phenomena in social media. There is a need for Artificial Intelligence(AI)based intervention which can filter hate content at scale. Most…

Neural text detectors are models trained to detect whether a given text was generated by a language model or written by a human. In this paper, we investigate three simple and resource-efficient strategies (parameter tweaking, prompt…

Lack of moderation in online communities enables participants to incur in personal aggression, harassment or cyberbullying, issues that have been accentuated by extremist radicalisation in the contemporary post-truth politics scenario. This…

Online conversations can be toxic and subjected to threats, abuse, or harassment. To identify toxic text comments, several deep learning and machine learning models have been proposed throughout the years. However, recent studies…

For automatically identifying hate speech and offensive content in tweets, a system based on a classical supervised algorithm only fed with character n-grams, and thus completely language-agnostic, is proposed by the SATLab team. After its…

Sentence-level attacks craft adversarial sentences that are synonymous with correctly-classified sentences but are misclassified by the text classifiers. Under the black-box setting, classifiers are only accessible through their feedback to…

This paper describes a novel study on using `Attention Mask' input in transformers and using this approach for detecting offensive content in both English and Persian languages. The paper's principal focus is to suggest a methodology to…