# Neural Word Decomposition Models for Abusive Language Detection

arXiv: https://arxiv.org/abs/1910.01043 · HTML: https://mlsanity.com/paper/1910.01043/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Oct 2019.

## Built on by (most cited first, 6 of 6)

- [Towards generalisable hate speech detection: a review on obstacles and solutions](https://mlsanity.com/paper/2102.08886/) (2021)
- [BERT-Beta: A Proactive Probabilistic Approach to Text Moderation](https://mlsanity.com/paper/2109.08805/) (2021)
- [Enriching Abusive Language Detection with Community Context](https://mlsanity.com/paper/2206.08445/) (2022)
- [Graph Convolutional Network for Swahili News Classification](https://mlsanity.com/paper/2103.09325/) (2021)
- [Improved two-stage hate speech classification for twitter based on Deep Neural Networks](https://mlsanity.com/paper/2206.04162/) (2022)
- [Detection of Abuse in Financial Transaction Descriptions Using Machine Learning](https://mlsanity.com/paper/2303.08016/) (2023)

## Abstract (arXiv)

User generated text on social media often suffers from a lot of undesired characteristics including hatespeech, abusive language, insults etc. that are targeted to attack or abuse a specific group of people. Often such text is written differently compared to traditional text such as news involving either explicit mention of abusive words, obfuscated words and typological errors or implicit abuse i.e., indicating or targeting negative stereotypes. Thus, processing this text poses several robustness challenges when we apply natural language processing techniques developed for traditional text. For example, using word or token based models to process such text can treat two spelling variants of a word as two different words. Following recent work, we analyze how character, subword and byte pair encoding (BPE) models can be aid some of the challenges posed by user generated text. In our work, we analyze the effectiveness of each of the above techniques, compare and contrast various word decomposition techniques when used in combination with others. We experiment with finetuning large pretrained language models, and demonstrate their robustness to domain shift by studying Wikipedia attack, toxicity and Twitter hatespeech datasets