I
Ivan Bretan
Researcher at Swedish Institute of Computer Science
Publications - 23
Citations - 586
Ivan Bretan is an academic researcher from Swedish Institute of Computer Science. The author has contributed to research in topics: Machine translation & Spoken language. The author has an hindex of 9, co-authored 23 publications receiving 581 citations.
Papers
More filters
Proceedings ArticleDOI
WEST: a Web browser for small terminals
Staffan Björk,Lars Erik Holmquist,Johan Redström,Ivan Bretan,Rolf Danielsson,Jussi Karlgren,Kristofer Franzén +6 more
TL;DR: WEST, a WEb browser for Small Terminals, is described, that aims to solve some of the problems associated with accessing web pages on hand-held devices through a novel combination of text reduction and focus+context visualization.
Proceedings Article
Spoken language translation with MID-90's technology: a case study.
Manny Rayner,Ivan Bretan,David Carter,Michael Collins,Vassilios Digalakis,Björn Gambäck,Jaan Kaja,Jussi Karlgren,Bertil Lyberg,Stephen Pulman,Patti Price,Christer Samuelsson +11 more
TL;DR: The architecture of the Spoken Language Translator (SLT), a prototype speech translation system which can translate queries from spoken English to spoken Swedish in the domain of air travel information systems, is described.
Assembling a Balanced Corpus from the Internet
TL;DR: The methodology for determining which genres to include is given, which is a double edged problem, involving both vaguely expressed user expectations and establishing categories using large numbers of features which taken singly have low predictive and explanatory power.
Proceedings ArticleDOI
A speech to speech translation system built from standard components
Manny Rayner,Hiyan Alshawi,Ivan Bretan,David Carter,Vassilios Digalakis,Björn Gambäck,Jaan Kaja,Jussi Karlgren,Bertil Lyberg,Steve Pulman,Patti Price,Christer Samuelsson +11 more
TL;DR: This paper describes a speech to speech translation system using standard components and a suite of generalizable customization techniques, and presents initial performance results.
Iterative Information Retrieval Using Fast Clustering and Usage-Specific Genres
TL;DR: This paper describes how collection specific empirically defined stylistics based genre prediction can be brought together together with rapid topical clustering to build an interactive information retrieval interface with multi-dimensional presentation of search results.