header

Improving Habitability of Natural Language Interfaces for Querying Ontologies With Feedback and Clarifcation Dialogues

25 Pages Posted: 7 Jul 2018 Publication Status: Accepted

See all articles by Danica Damljanovic

Danica Damljanovic

University of Sheffield - Department of Computer Science

Milan Agatonovic

The Fizzback Group

Hamish Cunningham

University of Sheffield - Department of Computer Science

Kalina Bontcheva

University of Sheffield - Department of Computer Science

Abstract

Natural Language Interfaces (NLIs) are a viable, human-readable alternative to complex, formal query languages like SPARQL, which are typically used for accessing semantically structured data (e.g.RDF and OWL repositories). However, in order to cope with natural language ambiguities, NLIs typically support a more restricted language. A major challenge when designing such restricted languages is habitability–how easily, naturally and effectively users can use the language to express themselves within the constraints imposed by the system. In this paper, we investigate two methods for improving the habitability of a Natural Language Interface: feedback and clarifcation dialogues. We model feedback by showing the user how the system interprets the query,thus suggesting repair through query reformulation. Next, we investigate how clarifcation dialogues can be used to control the query interpretations generated by the system. To reduce the cognitive overhead, clarifcation dialogues are coupled with a l earning mechanism. Both methods are shown to have a positive effect on the overall performance and habitability.

Keywords: Natural Language Interfaces, Ontologies, Question Answerin, Learning, Clarification Dialogues, User Interaction

Suggested Citation

Damljanovic, Danica and Agatonovic, Milan and Cunningham, Hamish and Bontcheva, Kalina, Improving Habitability of Natural Language Interfaces for Querying Ontologies With Feedback and Clarifcation Dialogues (February 8, 2013). Journal of Web Semantics First Look 19_0_1, Available at SSRN: https://ssrn.com/abstract=3198998 or http://dx.doi.org/10.2139/ssrn.3198998

Danica Damljanovic (Contact Author)

University of Sheffield - Department of Computer Science ( email )

Regent Court, 211 Portobello
Sheffield
United Kingdom

Milan Agatonovic

The Fizzback Group ( email )

London
United Kingdom

Hamish Cunningham

University of Sheffield - Department of Computer Science ( email )

Regent Court, 211 Portobello
Sheffield
United Kingdom

Kalina Bontcheva

University of Sheffield - Department of Computer Science ( email )

Regent Court, 211 Portobello
Sheffield
United Kingdom

Here is the Coronavirus
related research on SSRN

Paper statistics

Abstract Views
173
Downloads
2