Query answering over the web of data: the case of Afaan Oromo

Abstract

Nowadays, with the development of the Semantic Web, a lot of new structured data has become available on the Web in the form of knowledge bases. Query Answering over Web of Data is a field that has been widely explored in research area. Most current QA systems query on Web of Data, in one language (namely English). The existing approaches are not designed to be easily adaptable to new knowledge bases and languages. One of them is Afaan Oromo language. Research in Afaan Oromo Query Answering is still limited and has not reached the same level of English Query Answering due to the Afaan Oromo language specific challenges. Most of existing research in Afaan Oromo Query Answering has not explored the field of Query Answering on the web of data, and has mainly focused on natural language processing (NLP) and information retrieval from unstructured Afaan Oromo documents. The web is developing rapidly towards the notation of linked data where the data is linked by exploiting the semantic web technologies and standards. However, the variety of linked-data sources and their high heterogeneity make it difficult for humans to search and discover relevant information. As linked data is in RDF format, the standard approach would be to run structured queries in triple-pattern based languages like SPARQL, but only expert programmers are able to precisely specify their information needs. Users who have no knowledge with semantic web cannot express their queries in SPARQL. This problem can be fixed by using natural language interfaces that translate natural language queries to SPARQL. This study aims to make a step towards supporting Afaan Oromo Query Answering over Web of Data. The approach we propose to translate Afaan Oromo Natural language queries, to SPARQL. We have tested by using sample ontology on education domain to translate the user query to RDF triple and retrieve an answer from a RDF knowledge base. The proposed approach can process only on simple sentence query. The experimentation shows that the performance is on the average 66.03 % Recall, 76.17% Precision, and 71.63% F-measure.