2014 | OriginalPaper | Buchkapitel
Online Reasoning for Ontology-Based Error Detection in Text
verfasst von : Fernando Gutiererz, Dejing Dou, Stephen Fickas, Gina Griffiths
Erschienen in: On the Move to Meaningful Internet Systems: OTM 2014 Conferences
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Detecting error in text is a difficult task. Current methods use a domain ontology to identify elements in the text that contradicts domain knowledge. Yet, these methods require manually defining the type of errors that are expected to be found in the text before applying them. In this paper we propose a new approach that uses logic reasoning to detect errors in a statement from text online. Such approach applies Information Extraction to transform text into a set of logic clauses. The logic clauses are incorporated into the domain ontology to determine if it contradicts the ontology or not. If the statement contradicts the domain ontology, then the statement is incorrect with respect to the domain knowledge. We have evaluated our proposed method by applying it to a set of written summaries from the domain of Ecosystems. We have found that this approach, although depending on the quality of the Information Extraction output, can identify a significant amount of errors. We have also found that modeling elements of the ontology (i.e., property domain and range) likewise affect the capability of detecting errors.