FREyA: An interactive way of querying Linked Data using natural language (original) (raw)

Ontology Based Queries–Investigating a Natural Language Interface

2010

ABSTRACT In this paper we look at what may be learned from a comparative study examining non-technical users with a background in social science browsing and querying metadata. Four query tasks were carried out with a natural language interface and with an interface that uses a web paradigm with hyperlinks.

A text-based query interface to owl ontologies

2008

Abstract Accessing structured data in the form of ontologies requires training and learning formal query languages (eg, SeRQL or SPARQL) which poses significant difficulties for non-expert users. One of the ways to lower the learning overhead and make ontology queries more straightforward is through a Natural Language Interface (NLI). While there are existing NLIs to structured data with reasonable performance, they tend to require expensive customisation to each new domain or ontology.

Natural Language Interfaces to Ontologies: usability and performance (Transfer report)

2008

Abstract Accessing structured data in the form of ontologies currently requires the use of formal query languages (eg, SeRQL or SPARQL) which pose significant difficulties for non-expert users. One way to lower the learning overhead and make ontology queries more straightforward is through a Natural Language Interface (NLI). While there are existing NLIs to structured data with reasonable performance, they tend to require expensive customisation to each new domain or ontology.

Ontology-Based Natural Language Query Interfaces for Data Exploration

2018

Enterprises are creating domain-specific knowledge bases by curating and integrating all their business data, structured, unstructured and semi-structured, and using them in enterprise applications to derive better business decisions. One distinct characteristic of these enterprise knowledge bases, compared to the open-domain general purpose knowledge bases like DBpedia [16] and Freebase [6], is their deep domain specialization. This deep domain understanding empowers many applications in various domains, such as health care and finance. Exploring such knowledge bases, and operational data stores requires different querying capabilities. In addition to search, these databases also require very precise structured queries, including aggregations, as well as complex graph queries to understand the various relationships between various entities of the domain. For example, in a financial knowledge base, users may want to find out “which startups raised the most VC funding in the first qu...

Natural Language Interface for Querying Linked Data Using Case-Based Reasoning

Indian Journal of Computer Science and Engineering

With the emergence of Linked Data in RDF format, query systems should execute structured queries in SPARQL. Still, only expert programmers can specify their information needs and cope with Linked Data sources' diversity and heterogeneity. Therefore, understanding Natural Language (NL) queries to construct correct SPARQL queries is a great challenge for these query systems to access multiple heterogeneous semantic sources and Linked Data sets. This paper presents a new approach for querying Linked Data with NL queries. Our method identifies the topic and search criteria of the NL query based on the Case-Based Reasoning (CBR) technique. Next, we match the identified topic and search criteria to their corresponding entities in the dataset. Then, we represent the query as triples based on the semantic relations provided by the dataset. Finally, our system executes the SPARQL queries generated from the query triples, based on the proposed generation rules, to query the dataset and retrieve the relevant answers. Experiments showed that the proposed approach is efficient compared to the existing systems in terms of precision and recall.

ATHENA: An Ontology-Driven System for Natural Language Querying over Relational Data Stores

In this paper, we present ATHENA, an ontology-driven system for natural language querying of complex relational databases. Natural language interfaces to databases enable users easy access to data, without the need to learn a complex query language, such as SQL. ATHENA uses domain specific ontologies, which describe the semantic entities, and their relationships in a domain. We propose a unique two-stage approach, where the input natural language query (NLQ) is first translated into an intermediate query language over the ontology, called OQL, and subsequently translated into SQL. Our two-stage approach allows us to decouple the physical layout of the data in the relational store from the semantics of the query, providing physical independence. Moreover, ontologies provide richer semantic information, such as inheritance and membership relations, that are lost in a relational schema. By reasoning over the ontologies, our NLQ engine is able to accurately capture the user intent. We study the effectiveness of our approach using three different workloads on top of geographical (GEO), academic (MAS) and financial (FIN) data. ATHENA achieves 100% precision on the GEO and MAS workloads, and 99% precision on the FIN work-load which operates on a complex financial ontology. Moreover, ATHENA attains 87.2%, 88.3%, and 88.9% recall on the GEO,

An Intelligent Query Interface with Natural Language Support

Flairs, 2006

The project described by the present paper aims at building a bridge between Intelligent Query Interfaces and Natural Language Generation technologies. The idea is to have a query interface enabling the users to access heterogeneous data sources by means of an integrated ontology. This paper shows how we are redesigning our intelligent query interface by rendering the logic-based queries in natural language, leveraging the results achieved to-date by applied Systemic-Functional Linguistics.

Natural Language Query Processing for SPARQL generation - a Prototype System for SNOMEDCT

SPARQL queries are a powerful method for querying the large and increasing number of linked open data repositories available through the Semantic Web. However , generating SPARQL queries can be difficult, even for experts. Interfaces that accept questions in natural language and convert them to SPARQL queries are one solution to this problem. We describe the Linked Open Data Question Answering (LODQA) system. LODQA is developed to generate SPARQL queries from natural language, with the goal of providing an easy-to-use interface to search linked open RDF data. The paper presents a prototype version of LODQA which works on SNOMED CT, discussing the design and implementation, together with the limitations of the current implementation and future directions for improvement.