Semantic Web Enabled Geographic Question Answering Framework: GeoTR

TL;DR

This paper presents GeoTR, a framework that converts Turkish natural language questions into SPARQL queries for geographic data, utilizing a new Turkish ontology and hybrid NLP and linked data techniques.

Contribution

It introduces a novel Turkish geographic ontology and a hybrid question answering system converting natural language to SPARQL queries.

Findings

Developed a Turkish geographic ontology for linked data.

Created a system converting Turkish questions to SPARQL.

Addressed a gap in Turkish geographic question answering literature.

Abstract

With the considerable growth of linked data, researchers have focused on how to increase the availability of semantic web technologies to provide practical usages for real life systems. Question answering systems are an example of real-life systems that communicate directly with end users, understand user intention and generate answers. End users do not care about the structural query language or the vocabulary of the knowledge base where the point of a problem arises. In this study, a question answering framework that converts Turkish natural language input into SPARQL queries in the geographical domain is proposed. Additionally, a novel Turkish ontology, which covers a 10th grade geography lesson named Spatial Synthesis Turkey, has been developed to be used as a linked data provider. Moreover, a gap in the literature on Turkish question answering systems, which utilizes linked data in the geographical domain, is addressed. A hybrid system architecture that combines natural language processing techniques with linked data technologies to generate answers is also proposed. Further related research areas are suggested.