Xart: Discovery of correlated arguments of n-ary relations in text. (1st May 2017)

• Record Type: Journal Article
• Authors: Berrahou, Soumia Lilia; Buche, Patrice; Dibie, Juliette; Roche, Mathieu
• Is Part Of: Expert systems with applications. Volume 73(2017)
• Page Start: 115
• Page End: 124
• Publication Date: 2017-05-01
• Subjects: Information extraction -- N-ary relation -- Ontology -- Data mining -- Sequential pattern -- Quantitative data -- Linguistic pattern; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2016.12.028
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: We present Xart system for relevant quantitative data extraction from text. Xart system is based on a knowledge discovery process using a domain ontology. We propose a new edit measure to identify units of measure. We propose new enriched patterns with semantics for data extraction modeled as n-ary relations. Xart system is intended to help relevant complex data annotation in text. Abstract: Here we present the Xart system based on a three-step hybrid method using data mining approaches and syntactic analysis to automatically discover and extract relevant data modeled as n-ary relations in plain text. A n-ary relation links a studied object with its features considered as several arguments. We addressed the challenge of designing a novel method to handle the identification and extraction of heterogeneous arguments such as symbolic arguments, quantitative arguments composed of numbers and various measurement units. We thus developed the Xart system, which relies on a domain ontology for discovering patterns, in plain text, to identify arguments involved in n-ary relations. The discovered patterns take advantage of different ontological levels that facilitate identification of all arguments and pool them in the sought n-ary relation.