AR2SPARQL: An Arabic Natural Language Interface for the Semantic Web

Abstract

With the growing interest in supporting the Arabic language on the Semantic Web (SW), there is an emerging need to enable Arab users to query ontologies and RDF stores without being challenged with the formal logic of the SW. In the domain of English language, several efforts provided Natural Language (NL) interfaces to enable ordinary users to query ontologies using NL queries. However, none of these efforts were designed to support the Arabic language which has different morphological and semantic structures.As a step towards supporting Arabic Question Answering (QA) on the SW, this work presents AR2SPARQL, a NL interface that takes questions expressed in Arabic and returns answers drawn from an ontology-based knowledge base. The core of AR2SPARQL is the approach we propose to translate Arabic questions into triples which are matched against RDF data to retrieve an answer. The system uses both linguistic and semantic features to resolve ambiguity when matching words to the ontology content. To overcome the limited support for Arabic Natural Language Processing (NLP), the system does not make intensive use of sophisticated linguistic methods. Instead, it relies more on the knowledge defined in the ontology and the grammar rules we define to capture the structures of Arabic questions and to construct an adequate RDF representations. AR2SPARQL has been tested with two different datasets and results have shown that it achieves a good retrieval performance in terms of precision and recall.

Semantic Q&A System on the Qur’an

“…We leveraged the work done by [21], studied some of the queries that our system should be able to answer, and added more features and enhancements.…”

“…As mentioned before, most of the existing systems are designed to work with the English language, which is why we studied closely the NLI proposed by [21] where he tried to apply existing approaches to the Arabic language taking into account the characteristics and the format of the Arabic language. We leveraged the work done by [21], studied some of the queries that our system should be able to answer, and added more features and enhancements.…”

“…However, there is very little attempt to support querying content in other languages like Arabic using NL queries expressed in Arabic. The first research that has worked in implementing a NLI using Arabic language is AR2SPARQL [21] in 2015, AR2SPARQL proposed an Arabic portable NLI to ontologies and RDF data. Since this is one of the first to tackle this subject, we believe there is room for improvement to enhance the reasoning capabilities, ontology-matching process and co-reference resolution.…”

Machine-Translation History and Evolution: Survey for Arabic-English Translations

“…They also mentioned that the instant translators such as google, Bing, and more others are statistical translators and have no semantic processing in their works [12]. Alagha et al [51], presented a domain-independent approach to translating Arabic NL queries to SPARQL by getting benefits from the linguistic analysis [51]. It was just to translate the Arabic questions to SPARQL, not to other human-languages.…”

Toward an Arabic Question Answering System over Linked Data

“…It uses supervised support vector machine (SVM) classifier for question classification and answer selection, to generate the exact answer for a given question in Arabic natural language. AR2SPARQL [37] is an Arabic natural language interface for semantic Web, which uses linguistic and semantic analysis to convert the Arabic query into RDF triples, which are then matched with ontology triples to retrieve an answer.…”