Abstract—Fact extraction methods are used for various aims. Here, a new method is introduced for a new application – computing semantic relatedness of texts. Ontological facts are the facts about real world that are available in a knowledgebase called ontology. There are many systems to extract ontological facts from a text. State-of-the-art of these systems is SOFIE that is not appropriate to compute semantic relatedness of texts. In this paper, this problem will be explained and a new ontological facts extraction system is introduced that is appropriate for computing semantic relatedness of texts. For this aim, YAGO ontology will be used as a background knowledge and facts resource. In final it will be suggested that using YAGO relations can optimize ontological facts extraction system.
Index Terms—Ontological facts, semantic relatedness, disambiguation, semantic entity extraction, YAGO ontology.
Farhad Abedini is with the Electrical and Computer Engineering Department, and member of Young Researchers Club, Islamic Azad University, Roudsar and Amlash branch, Roudsar, Iran (e-mail: abedini.ac@gmail.com).
Seyedeh Masoumeh Mirhashem is with the Islamic Azad University, Roudsar and Amlash branch, Roudsar, Iran (e-mail: saeedeh.mirhashem@yahoo.com).
Cite: Farhad Abedini and Seyedeh Masoumeh Mirhashem, "From Text to Facts: Recognizing Ontological Facts for a New Application," International Journal of Machine Learning and Computing vol. 2, no. 3, pp. 183-187, 2012.