A logic-based relational learning approach to relation extraction: The OntoILPER system. (February 2019)

• Record Type: Journal Article
• Authors: Lima, Rinaldo; Espinasse, Bernard; Freitas, Fred
• Is Part Of: Engineering applications of artificial intelligence. Volume 78(2019)
• Page Start: 142
• Page End: 157
• Publication Date: 2019-02
• Subjects: Relation extraction -- Rule induction -- Information extraction -- Inductive logic programming -- Relational learning; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2018.11.001
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Relation Extraction (RE), the task of detecting and characterizing semantic relations between entities in text, has gained much importance in the last two decades, mainly in the biomedical domain. Many papers have been published on Relation Extraction using supervised machine learning techniques. Most of these techniques rely on statistical methods, such as feature-based and tree-kernels-based methods. Such statistical learning techniques are usually based on a propositional hypothesis space for representing examples, i.e., they employ an attribute–value representation of features. This kind of representation has some drawbacks, particularly in the extraction of complex relations which demand more contextual information about the involving instances, i.e., it is not able to effectively capture structural information from parse trees without loss of information. In this work, we present OntoILPER, a logic-based relational learning approach to Relation Extraction that uses Inductive Logic Programming for generating extraction models in the form of symbolic extraction rules. OntoILPER takes profit of a rich relational representation of examples, which can alleviate the aforementioned drawbacks. The proposed relational approach seems to be more suitable for Relation Extraction than statistical ones for several reasons that we argue. Moreover, OntoILPER uses a domain ontology that guides the background knowledge generation process and is used for storing the extracted relation instances. The induced extraction rules were evaluated on three protein–protein interaction datasets from the biomedical domain. The performance of OntoILPER extraction models was compared with other state-of-the-art RE systems. The encouraging results seem to demonstrate the effectiveness of the proposed solution. Highlights: A relation extraction (RE) method based on ILP is proposed. Inductive Logic Programming is used to induce extraction rules. The proposed solution uses a domain ontology for guiding the extraction process. Comparative experiments with kernel-based RE systems are provided. The proposed method for RE is very competitive with kernel-based systems using SVM.