Year: 2011
Type: dissertation
Abstract: Accessing structured data in the form of ontologies currently requires the use \nof formal query languages (e.g., SeRQL or SPARQL) which pose significant \ndifficulties for non-expert users. One way to lower the learning overhead \nand make ontology queries more straightforward is through a Natural Lan- \nguage Interface (NLI). While there are existing NLIs to structured data \nwith reasonable performance, they tend to require expensive customisation \nto each new domain. Additionally, they often require specific adherence to \na pre-defined syntax which, in turn, means that users still have to undergo \ntraining. \nIn this thesis, we study the usability of NLIs from two perspectives: that of \nthe developer who is customising the NLI system, and that of the end-user \nwho uses it for querying. We investigate whether usability methods such \nas feedback and clarification dialogs can increase the usability for end users \nand reduce the customisation effort for the developers. To that end, we have \ndeveloped two systems, QuestIO and FREyA, whose design, evaluation and \ncomparison with similar systems form the core of the contribution of this \nthesis. \n
Author: Danica Damljanović
Language: English
Topic: Semantic Web and Ontologies
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W1526253363