# Improving Automatic Hate Speech Detection with Multiword Expression Features

arXiv: https://arxiv.org/abs/2106.00237 · HTML: https://mlsanity.com/paper/2106.00237/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 29 references that are in the map.
- First posted on arXiv 1 Jun 2021.

## Builds on (most cited first, 10 of 10)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Supervised Learning of Universal Sentence Representations from Natural Language Inference Data](https://mlsanity.com/paper/1705.02364/) (2017)
- [Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior](https://mlsanity.com/paper/1802.00393/) (2018)
- [Deep Learning for Hate Speech Detection in Tweets](https://mlsanity.com/paper/1706.00188/) (2017)
- [A BERT-Based Transfer Learning Approach for Hate Speech Detection in Online Social Media](https://mlsanity.com/paper/1910.12574/) (2019)
- [Mean Birds: Detecting Aggression and Bullying on Twitter](https://mlsanity.com/paper/1702.06877/) (2017)
- [Comparative Studies of Detecting Abusive Language on Twitter](https://mlsanity.com/paper/1808.10245/) (2018)
- [MTLB-STRUCT @PARSEME 2020: Capturing Unseen Multiword Expressions Using Multi-task Learning and Pre-trained Masked Language Models](https://mlsanity.com/paper/2011.02541/) (2020)
- [SHOMA at Parseme Shared Task on Automatic Identification of VMWEs: Neural Multiword Expression Tagging with High Generalisation](https://mlsanity.com/paper/1809.03056/) (2018)

## Abstract (arXiv)

The task of automatically detecting hate speech in social media is gaining more and more attention. Given the enormous volume of content posted daily, human monitoring of hate speech is unfeasible. In this work, we propose new word-level features for automatic hate speech detection (HSD): multiword expressions (MWEs). MWEs are lexical units greater than a word that have idiomatic and compositional meanings. We propose to integrate MWE features in a deep neural network-based HSD framework. Our baseline HSD system relies on Universal Sentence Encoder (USE). To incorporate MWE features, we create a three-branch deep neural network: one branch for USE, one for MWE categories, and one for MWE embeddings. We conduct experiments on two hate speech tweet corpora with different MWE categories and with two types of MWE embeddings, word2vec and BERT. Our experiments demonstrate that the proposed HSD system with MWE features significantly outperforms the baseline system in terms of macro-F1.