 |
Central and Eastern European Survey
Department of Intelligent Systems
Jozef Stefan Institute Research
Research Activities pursued at the organisation
The work at the department mostly centres around machine learning in different frameworks (e.g. inductive logic programming and genetic algorithms) and for different domains (e.g. medicine, ecology). The department is also involved in the field of computational linguistics. In the past, research dealt with finite-state and feature-structure models of morphology and syntactic descriptions of the Slovene language in the framework of HPSG. In recent years the focus has shifted to other areas, and more towards the field of human language technologies. One area of concentration is corpus linguistics, in particular the development of SGML / TEI annotated textual corpora of Slovene language. This is being complemented with consulting in the area of SGML technologies. In tandem with building corpora, other resources (e.g. lexica) and methods (e.g. tagging) for the Slovene language are being developed. Given this development of annotated and validated 'learning sets' for Slovene language, methods of machine-learning (Slovene) linguistic structure are also being investigated; we have, so far, used mainly Inductive Logic Programming as the learning paradigm. Another research area is the development of new approaches that will enable addressing different problems of Text and Web data analysis by applying Machine Learning and Data Mining methods. The research has so far concentrated on the development of an automatic Web page taxonomy builder and classifier. We are also involved in speech technologies, with the focus on building text-to-speech systems for Slovene.
This page is no longer maintained. Please visit http://www.elsnet.org/survey/quests to find out how to update your organisation profile or to find information about this organisation
| [Survey] [Organisation] [General Info] [Training] [Resources] [Research] [Staff] [Publications] |