Neural-Symbolic Learning

Investigating logic tensor networks for neural-symbolic argument mining
Logic Tensor Networks train argument mining models to fit the data and satisfy domain rules, which improves classification, rule compliance, and robustness on scientific abstracts.
PDF Cite
Neural-Symbolic Argumentation Mining: An Argument in Favor of Deep Learning and Reasoning
Argues that argument mining needs reasoning, and that neural-symbolic and statistical relational learning can join deep networks and logic rules to provide it.
Andrea Galassi, Kristian Kersting, Marco Lippi, Xiaoting Shao, Paolo Torroni
Cite DOI URL
The force awakens: Artificial intelligence for consumer law
A position paper that argues AI can serve consumers, not only businesses, by analyzing contracts, privacy policies, ads, and app code at scale.
Marco Lippi, Giuseppe Contissa, Agnieszka Jabłonowska, Francesca Lagioia, Hans-Wolfgang Micklitz, Przemysław Pałka, Giovanni Sartor, Paolo Torroni
Cite DOI