Total Recall

Yesterday, May 15, Erich Hegenberger of Total Recall ApS presented “Snowball - no longer lost in translation” to an audience of roughly 100 language professionals at the Language Technology Forum held by the Centre for Language Technology at the University of Copenhagen. The presentation focused on some key features of Snowball, such as the user-definable popup translation window with its list of translations scrolling to track the words the user selects in the source, computer translation suggestions, and Snowball’s amazing ability to work completely in the background, invisibly storing translation memory segments as the user works and popping up to help only when it recognizes something it’s seen before.

During the coffee and lunch breaks, the Snowball table was heavily visited, with lots of researchers and translators interested in seeing Snowball work. It was hard to get a break away from the table, and most of the time we could have used a few extra people on hand to help demonstrate the program and answer questions.

The complete presentation can be viewed here.

Other forum presenters:

Also of special interest in TM developments, Eric Rhode, Sales Manager for WebWordSystem, explained his company’s unique vision for a globally networked system of private and public translation memory databases. This system can give language professionals access to a vast resource of knowledge and information.

Lisbeth Kjeldgaard Almsten of Inter-Set Translations discussed translation memory and other translation tools from a user perspective. Almsten cautioned that, although translation tools can be highly effective, they have to be used with care to ensure a high-quality result. From the Danish offices of Lionbridge, Administrative Director Angelique Espensen discussed Lionbridge’s development of in-house language tools such as Logoport and Freeway 2.0, along with the corporation’s many other services.

Other presenters were Dr. Eckhard Bick of GramTrans (machine translation) researcher Juergen Wedekind from the Centre for Language Technology (bilingual terminology extraction), Anne Jensen of the Journal of Danish Parliamentary Proceedings Folketingstidende (speech to text) and Jens Otto Kjaerum and Stefan Pal of the Prolog Development Center (text to speech).

In his closing presentation summarizing the day’s experiences, Dr. Steven Krauwer of the Utrecht Institute of Linguistics at Utrecht University in Holland praised Snowball for ‘making the computer invisible’. He also spoke fondly of his own past R&D work in machine translation, especially EUROTRA as well as other ongoing EC projects, and presented his outlook for the future of language technology.

Acknowledgements
Many thanks to Lina Henriksen and Dorte Haltrup Hansen of the Centre for Language Technology for the kind invitation and for the last-minute help, and to all those who visited the Snowball table with their questions and feedback!