A logic-based relational learning approach to relation extraction: The OntoILPER system

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.

OntoED: Low-resource Event Detection with Ontology Embedding

“…Different from , we propose to revisit the ED task as an ontology learning process, inspired by relation extraction (RE) tasks based on ontology and logic-based learning. Lima et al (2018Lima et al ( , 2019 present a logic-based relational learning approach to RE that uses inductive logic programming for generating information extraction (IE) models in the form of symbolic rules, demonstrating that ontology-based IE approaches are advantageous in capturing correlation among classes, and succeed in symbolic reasoning.…”

An encoder–decoder approach to mine conditions for engineering textual data

“…It applies several methods to extract entity-relations to the same piece of text and computes a level of confidence. Lima et al (2019) described a logic-based relational learning approach that uses inductive logic programming to learn symbolic extraction rules. It uses a domain ontology that guides the background knowledge generation process and is used for storing the extracted relation instances.…”

“…Many entity-relation extractors (Etzioni et al, 2011;Velásquez et al, 2011;Yang and Soo, 2012;Vicient et al, 2013;Mitchell et al, 2015;Lima et al, 2019) and opinion miners (Perikos and Hatzilygeroudis, 2016;Jin et al, 2016a,b;Zhang et al, 2016;Pablos et al, 2018;Yoo et al, 2018;Ducange et al, 2019) have been analysed in this article. The conclusion is that they have a common problem: they do not take conditions into account.…”

The Impact of Semantic Linguistic Features in Relation Extraction: A Logical Relational Learning Approach

“…The main contribution of this paper consists in the experimental validation of our working hypothesis that a feature engineering step composed by a substantial body of deep linguistic knowledge in combination with an expressive inductive learning technique can generate effective RE models. For testing this hypothesis, a LRL RE system (Lima et al, 2017;Lima et al, 2019) was used. The remainder of this section describes the RE system, the rich feature engineering component, and the underlying model for representing semantic features.…”