ADANS: An agriculture domain question answering system using ontologies

Abstract

The research area of Question Answering (QA) is explored widely to provide an accurate answer to questions asked in natural languages. In the deep ocean of information, the Web, searching for a concise answer is quite a time taking task. The QA system does this task on behalf of the questioner. Recently with the introduction of the semantic web, the web is progressing towards linked data. This data is available in the form of Resource Description Format(RDF) and Web Ontology Language(OWL). Querying this data requires the query to be expressed in SPARQL Protocol and RDF Query Language(SPARQL). This paper presents a QA system on agriculture domain, the ADANS, to answer queries given in natural language. The system uses a combination of Natural Language Processing(NLP) and semantic web technologies. The system formulates an SPARQL from the queries given in natural language. The query loosening part of the system helps in retrieving some less precise answers in acceptable time.