About Norms and Causes

Daniel Kayser (1) , Farid Nouioua (1)

1 LIPN - Laboratoire d'Informatique de Paris-Nord

Knowing the norms of a domain is crucial, but there exists no repository of norms. We propose a method to extract them from texts: narrative texts generally do not describe a norm, but rather the discrepancies between what actually happened, and the corresponding normal sequence of events. Answers about the causes of an event often reveal the implicit norms. We apply this idea to the domain of driving, and validate it by designing algorithms that identify, in a text, the “basic” norms to which it refers implicitly.

Mots clés: Natural Language Understanding, Norms, Non-monotonic Logic, Causal reasoning, Natural Language Semantics

Domaines: Intelligence artificielle [cs.AI]

Daniel Kayser, Farid Nouioua. About Norms and Causes. International Journal on Artificial Intelligence Tools, 2005, 14(1-2), pp.7-23. ⟨hal-00085144⟩