Using Linguistic Analysis to Translate Arabic Natural Language Queries to SPARQL

摘要

The logic-based machine-understandable framework of the Semantic Web oftenchallenges naive users when they try to query ontology-based knowledge bases.Existing research efforts have approached this problem by introducing NaturalLanguage (NL) interfaces to ontologies. These NL interfaces have the ability toconstruct SPARQL queries based on NL user queries. However, most efforts wererestricted to queries expressed in English, and they often benefited from theadvancement of English NLP tools. However, little research has been done tosupport querying the Arabic content on the Semantic Web by using NL queries.This paper presents a domain-independent approach to translate Arabic NLqueries to SPARQL by leveraging linguistic analysis. Based on a specialconsideration on Noun Phrases (NPs), our approach uses a language parser toextract NPs and the relations from Arabic parse trees and match them to theunderlying ontology. It then utilizes knowledge in the ontology to group NPsinto triple-based representations. A SPARQL query is finally generated byextracting targets and modifiers, and interpreting them into SPARQL. Theinterpretation of advanced semantic features including negation, conjunctiveand disjunctive modifiers is also supported. The approach was evaluated byusing two datasets consisting of OWL test data and queries, and the obtainedresults have confirmed its feasibility to translate Arabic NL queries toSPARQL.