Neural-Symbolic Argumentation Mining: An Argument in Favor of Deep Learning and Reasoning

Abstract

Deep learning is bringing remarkable contributions to the field of argumentation mining, but the existing approaches still need to fill the gap towards performing advanced reasoning tasks. In this position paper, we posit that neural-symbolic and statistical relational learning could play a crucial role in the integration of symbolic and sub-symbolic methods to achieve this goal.

Andrea Galassi

Junior Assistant Professor

He is an expert in deep learning architectures for natural language processing.

Marco Lippi

Associate Professor

He is an expert in machine learning and deep learning, with applications in many domains including natural language processing.

Paolo Torroni

Associate Professor

Head of the Language Technologies lab. His main research focus is in artificial intelligence, and in particular natural language processing, multi-agent systems, and computational logics.