We are interested in developing deep learning models that are capable of employing knowledge in the form of natural language. Such knowledge is easy to interpret and to define (compared to structured representations like syntactic trees, knowledge graphs and symbolic rules). Unstructured knowledge increases the interpretability of models and goes in the direction of defining a realistic type of artificial intelligence. However, properly integrating this type of information is particularly challenging due to its inherent ambiguity and variability.
Evaluate how models are affected by definitions of abusive and hate speech to promote awareness in developing accurate abusive speech detection systems
Train classifiers with guidelines only, without the need of classification labels during training