Developing an Arabic Infectious Disease Ontology to Include Non-Standard Terminology

Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 4842–4850 Marseille, 11–16 May 2020 c⃝ European Language Resources Association (ELRA), licensed under CC-BY-NC 4842 Developing an Arabic Infectious Disease Ontology to Include Non-Standard Terminology Lama Alsudias1 2 and Paul Rayson1 1School of Computing and Communications, Lancaster University, UK 2College of Computer and Information Science, King Saud University, Saudi Arabia lalsudias@ksu.edu.sa, p.rayson@lancaster.ac.uk Abstract Building ontologies is a crucial part of the semantic web endeavour. In recent years, research interest has grown rapidly in supporting languages such as Arabic in NLP in general but there has been very little research on medical ontologies for Arabic. We present a new Arabic ontology in the infectious disease domain to support various important applications including the monitoring of infectious disease spread via social media. This ontology meaningfully integrates the scientific vocabularies of infectious diseases with their informal equivalents. We use ontology learning strategies with manual checking to build the ontology. We applied three statistical methods for term extraction from selected Arabic infectious diseases articles: TF-IDF, C-value, and YAKE. We also conducted a study, by consulting around 100 individuals, to discover the informal terms related to infectious diseases in Arabic. In future work, we will automatically extract the relations for infectious disease concepts but for now these are manually created. We report two complementary experiments to evaluate the ontology. First, a quantitative evaluation of the term extraction results and an additional qualitative evaluation by a domain expert. Keywords: Arabic, infectious disease, NLP, Ontology 1. Introduction Ontologies are formal representations of concepts and their relationships in machine readable form. Ontologies can be built manually, semi-automatically or automat- ically. Generally, they fall into two categories: Upper level Ontology and Domain Ontology. There are many existing ontologies in English and other languages but for Arabic there has been little recent research. Developing ontologies from Arabic text is a difficult process due to the lack of existing resources and the nature of the Arabic language which has complex grammatical, morphologi- cal and semantic aspects. Existing NLP algorithms for other languages cannot simply be applied directly on Arabic. In addition, the Arabic language has many dialects which may complicate ambiguities for computational understanding of the meaning of the words and reduce the accuracy of tools created only for Modern Standard Arabic. In this paper, we present a new Arabic Ontology from the infectious disease domain. The overall goal of this ontology is to be a key source of information related to infectious diseases in Arabic. We envisage that it can be used for many important applications in academia and the real world including Question Answering on the Semantic Web (AlAgha and Abu-Taha, 2015) and, in particular in our case, for online monitoring of health events (Collier et al., 2010). The rest of paper is organised as follows. Section 2 cov- ers related background work. Section 3 explains the re- quirement for an Infectious Disease Ontology in Arabic. The Ontology Engineering process includes Ontology Ar- chitecture, Data Gathering, …

Content truncated to 500 words