Use this url to cite publication: https://hdl.handle.net/20.500.14911/142776
The use of the natural language understanding agents with conceptual models
Publication Type (CRIS)
Straipsnis konferencijos medžiagoje Web of Science duomenų bazėje / Article in conference proceedings in Web of Science database (P1a1)
Publication Type (eLABa)
Straipsnis konferencijos darbų leidinyje Web of Science DB / Article in conference proceedings Web of Science DB (P1a)
Title [en]
The use of the natural language understanding agents with conceptual models
Olegas Vasilecas, Algirdas Laukaitis
Is part of
ICEIS 2006: proceedings of the Eighth international conference on Enterprise information systems: artificial intelligence and decision support systems. Paphos, Cyprus, May 23-27, 2006 / INSTICC - Institute for Systems and Technologies of Information, Control and Communication : Springer, 2006
Published In
| Year | Start Page | End Page |
|---|---|---|
2006 | 308 | 311 |
Referenced in Database(s)(DBs)
Extent
p. 308-311
Science / Art Area
Technologijos mokslai / Technological sciences (T)
Field of Science / Art
Informatikos inžinerija / Informatics engineering (T007)
Abstract (en)
In this paper AI agents for natural language interfaces in data exploration domain are presented. The experiment done with the IBM natural language toolbox has shown that the black box approach in this case leads to misclassification. Unsatisfactory results of the experiment triggered the present research aimed at improving the user interface with the natural language modality at architectural and algorithm levels. We extended traditional natural language interfaces in data exploration domain in the following direction: the use of feedforward neural network as concepts indexes in the users natural language interfaces are suggested. All presented concepts are realized as the open source project JMining Dialog.
Resource Type (COAR)
TextConference outputConference proceedingsConference paper
Language
Anglų / English (en)
Country
Lietuva / Lithuania (LT)
Owning collection
eLABa ID
3767216