Automated conversion from natural language query to SPARQL query
- PDF / 1,003,712 Bytes
- 20 Pages / 439.642 x 666.49 pts Page_size
- 73 Downloads / 239 Views
Automated conversion from natural language query to SPARQL query Haemin Jung1
· Wooju Kim1,2
Received: 20 July 2019 / Revised: 8 November 2019 / Accepted: 11 November 2019 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Nowadays, domain ontologies are widely used as background knowledge bases. However, end users of ontology-based question answering (QA) systems are unaware of major concepts of ontology or the structure of domain ontology schema. Thus, it has been essential to provide an efficient method to reduce this gap. Namely, the critical issue for ontologybased QA systems is how to generate a SPARQL query from a user’s natural language query (NLQ). Therefore, we proposed a method to generate SPARQL queries from Korean natural language queries. When an input query comes in, we split it into a set of tokens and map each token to certain resources in the ontology. Subsequently, a graph generation process creates multiple “query graphs” by arranging the resources and identifying relationships between them. To identify relations between resources, we applied a path search algorithm based on the structure of domain ontology schema. We score query graphs by measuring the degree to which the graph reflected the general user’s intent, and the best-rated query graph is converted into a SPARQL query. We implemented a prototype system to evaluate the proposed method for the music domain ontology and conclude that our query conversion process can convert Korean natural language queries into semantically equivalent SPARQL queries. We anticipate that, after appropriate modification, the process can be applied to other languages. Keywords SPARQL generation · Domain ontology · Natural language query · Korean language
Wooju Kim
Haemin Jung [email protected] 1
Smart Systems Lab, Department of Industrial Engineering, Yonsei University, Seoul, Republic of Korea
2
Present address: Seoul, Republic of Korea
Journal of Intelligent Information Systems
1 Introduction Nowadays, many question answering (QA) systems use domain ontology as their background knowledge base. Domain ontologies are widely used as data repositories because they have several advantages over traditional relational databases. Unlike relational databases, which manage concepts using a set of tables, domain ontologies can store the meaning of concepts and the semantic relationships between them. Additionally, based on web standards such as Resource Description Framework (RDF) and Web Ontology Language (OWL), domain ontologies possess rich expressiveness and are able to process more “semantic” queries. Another web standard, SPARQL, which is an RDF query language, is used to construct the queries for semantic search. However, there are some challenges faced by domain ontology-based QA systems. One of the most important issues is the difficulty in interpreting user queries. In particular, the necessity to process natural language queries has increased as voice controlled devices such as smart speakers become increasingly co
Data Loading...
