Leveraging Dependency Grammar for Fine-Grained Offensive Language Detection using Graph Convolutional Networks

Abstract

In this paper, we address the problem of offensive language detection on Twitter, while also detecting the type and the target of the offence. We propose a novel approach called SyLSTM, which integrates syntactic features in the form of the dependency parse tree of a sentence and semantic features in the form of word embeddings into a deep learning architecture using a Graph Convolutional Network. Results show that the proposed approach significantly outperforms the state-of-the-art BERT model with orders of magnitude fewer number of parameters.

Publication
The 10th International Workshop on Natural Language Processing for Social Media (SocialNLP ‘22)