A Roadmap for Neuro-argumentative Learning

Computational argumentation (CA) has emerged, in recent decades, as a powerful formalism for knowledge representation and reasoning in the presence of conflicting information, notably when reasoning non-monotonically with rules and exceptions. Much existing work in CA has focused, to date, on reasoning with given argumentation frameworks (AFs) or, more recently, on using AFs, possibly automatically drawn from other systems, for supporting forms of XAI. In this short paper we focus instead on the problem of learning AFs from data, with a focus on neuro-symbolic approaches. Specifically, we overview existing forms of neuro-argumentative (machine) learning, resulting from a combination of neural machine learning mechanisms and argumentative (symbolic) reasoning. We include in our overview neuro-symbolic paradigms that integrate reasoners with a natural understanding in argumentative terms, notably those capturing forms of non-monotonic reasoning in logic programming. We also outline avenues and challenges for future work in this spectrum.

Authors

• Maurizio Proietti
• Francesca Toni

Keywords

• Computational argumentation
• Artificial neural networks
• Non-monotonic reasoning