Using a SMT solver for risk analysis: detecting logical mistakes in texts

Florence Dupin de Saint-Cyr (1, 2) , Marie-Christine Lagasquie-Schiex (1, 2) , William Raynaut (3) , Patrick Saint Dizier (1, 4)

1 IRIT-ADRIA - Argumentation, Décision, Raisonnement, Incertitude et Apprentissage
2 UT3 - Université Toulouse III - Paul Sabatier
3 IRIT-SIG - Systèmes d’Informations Généralisées
4 CNRS - Centre National de la Recherche Scientifique

The purpose of this paper is to describe some results of the LELIE project, that are a contribution of Artificial Intelligence to a special domain: the analysis of the risks due to poorly written technical documents. This is a multidisciplinary contribution since it combines natural language processing with logical satisfiability checking. This paper explains how satisfiability checking can be used for detecting inconsistencies, redundancy and incompleteness in procedural texts and describes the part of the implemented tool that produces the logical translation of technical texts and realizes the checkings.

Mots clés: Knowledge Representation; AI in Natural Language Processing and Understanding; Reasoning

Domaines: Intelligence artificielle [cs.AI]; Informatique et langage [cs.CL]; Apprentissage [cs.LG]; Logique en informatique [cs.LO]

Florence Dupin de Saint-Cyr, Marie-Christine Lagasquie-Schiex, William Raynaut, Patrick Saint Dizier. Using a SMT solver for risk analysis: detecting logical mistakes in texts. International Conference on Tools with Artificial Intelligence - ICTAI 2014, Nov 2014, Limassol, Cyprus. pp. 867-874, ⟨10.1109/ICTAI.2014.133⟩. ⟨hal-01147277⟩