Lightweight predicate extraction for patient-level cancer information and ontology development

Muhammad Amith,Hua Xu,Yaoyun Zhang,Cui Tao,Hsing-Yi Song

doi:10.1186/s12911-017-0465-x

Abstract

BackgroundKnowledge engineering for ontological knowledgebases is resource and time intensive. To alleviate these issues, especially for novices, automated tools from the natural language domain can assist in the development process of ontologies. We focus towards the development of ontologies for the public health domain and use patient-centric sources from MedlinePlus related to HPV-causing cancers.MethodsThis paper demonstrates the use of a lightweight open information extraction (OIE) tool to derive accurate knowledge triples that can lead to the seeding of an ontological knowledgebase. We developed a custom application, which interfaced with an information extraction software library, to help facilitate the tasks towards producing knowledge triples from textual sources.ResultsThe results of our efforts generated accurate extractions ranging from 80–89% precision. These triples can later be transformed to OWL/RDF representation for our planned ontological knowledgebase.ConclusionsOIE delivers an effective and accessible method towards the development ontologies.

Highlights

Knowledge engineering for ontological knowledgebases is resource and time intensive
MedlinePlus is a website produced by the National Institutes of Health (NIH) that provides health information curated for patients, their families and friends, and other consumers [30]
The general objective of this paper is to assess the feasibility of utilizing open information extraction tools, ClausIE, to aid in the retrieval of knowledge triples or n-ary tuples for ensuing encoding into an ontology

Summary

Introduction

Knowledge engineering for ontological knowledgebases is resource and time intensive To alleviate these issues, especially for novices, automated tools from the natural language domain can assist in the development process of ontologies. A hybrid approach where manual development is augmented by automating some of the process would be a more feasible option to ease the initial development for ontology development With human assistance, this would ensure that the development process is accurate, and advance any new knowledge on how to fully automate the workflow and technology based on lessons learned. This paper will introduce the use of open information extraction (OIE) to assist in the initial phase of extracting and filtering meaningful knowledge from resources, patient-level cancer information from MedlinePlus [5]. We posit that open information extraction will elicit accurate extraction of knowledge tuples from patient-level textual sources for ontology engineering

Objectives

Methods

Results

Discussion

Conclusion