Evaluating the usability of natural language query languages and interfaces to Semantic Web knowledge bases

Abstract

The need to make the contents of the Semantic Web accessible to end-users becomes increasingly pressing as the amount of information stored in ontology-based knowledge bases steadily increases. Natural language interfaces (NLIs) provide a familiar and convenient means of query access to Semantic Web data for casual end-users. While several studies have shown that NLIs can achieve high retrieval performance as well as domain independence, this paper focuses on usability and investigates if NLIs and natural language query languages are useful from an enduser's point of view. To that end, we introduce four interfaces each allowing a different query language and present a usability study benchmarking these interfaces. The results of the study reveal a clear preference for full natural language query sentences with a limited set of sentence beginnings over keywords or formal query languages. NLIs to ontology-based knowledge bases can, therefore, be considered to be useful for casual or occasional end-users. As such, the overarching contribution is one step towards the theoretical vision of the Semantic Web becoming reality. The need to make the contents of the Semantic Web accessible to end-users becomes increasingly pressing as the amount of information stored in ontology-based knowledge bases steadily increases. Natural language interfaces (NLIs) provide a familiar and convenient means of query access to Semantic Web data for casual end-users. While several studies have shown that NLIs can achieve high retrieval performance as well as domain independence, this paper focuses on usability and investigates if NLIs and natural language query languages are useful from an enduser's point of view. To that end, we introduce four interfaces each allowing a different query language and present a usability study benchmarking these interfaces. The results of the study reveal a clear preference for full natural language query sentences with a limited set of sentence beginnings over keywords or formal query languages. NLIs to ontology-based knowledge bases can, therefore, be considered to be useful for casual or occasional end-users. As such, the overarching contribution is one step towards the theoretical vision of the Semantic Web becoming reality. DOI AbstractThe need to make the contents of the Semantic Web accessible to end-users becomes increasingly pressing as the amount of information stored in ontology-based knowledge bases steadily increases. Natural language interfaces (NLIs) provide a familiar and convenient means of query access to Semantic Web data for casual end-users. While several studies have shown that NLIs can achieve high retrieval performance as well as domain independence, this paper focuses on usability and investigates if NLIs and natural language query languages are useful from an enduser's point of view. To that end, we introduce four interfaces each allowing a different query language and present a usability study benchmarking these interfaces. The results of the study reveal a clear prefer...

Experiencing OptiqueVQS: a multi-paradigm and ontology-based visual query system for end users

“…Nevertheless, keyword search stands as a good option in terms of accessibility, learnability and efficiency, since it does not demand any expert knowledge and skills. Natural query interfaces (e.g., [48,91]) go beyond the keyword search; this is due to the fact that they interpret a query as whole and take linguistic considerations into account. However, they do not achieve much in terms of accuracy and completeness due to the ambiguity of natural language; some approaches try to alleviate this issue, such as by acquiring feedback and clarification through user dialogues (e.g., [25,58]), yet this increases the user cognitive load.…”

Linked Biomedical Dataspace: Lessons Learned Integrating Data for Drug Discovery

“…Existing vocabularies e.g. VoID [1], DCAT 19 , Dublin Core (DC) 20 , and FOAF 21 can be used to describe data in the catalogue. The selection of a vocabulary depends upon the purpose of the catalogue and the granularity under consideration.…”

“…Even for a skilled LD practitioner it is difficult to assemble federated queries. An interface, which effectively lowers the barrier between Usability (Natural ) and Expressivity (Formal ), should be developed [20]. Such an interface evolves through 5 distinct stages -SPARQL, VQS, Single entity search, Keyword search and Google-like NL-queries.…”

“…compulsory selection of the Drug concept to retrieve information on Aspirin [18]. Primarily, an exhaustive dictionary summarizing all types of 'biological entities' should be compiled using machine-learning term extraction [34] and the gap could then be bridged further by proposed methodologies [12,20].…”

Free-Text Search over Complex Web Forms

“…ways to ll out the complex web form) as results. Kaufmann and Bernstein showed the importance of guiding the user during the query formulation process [2].…”