Universiteit van Amsterdam

Events

Institute for Logic, Language and Computation

Please note that this newsitem has been archived, and may contain outdated information or links.

12 December 2007, Computational Linguistics Seminar, Philipp Koehn

Speaker: Philipp Koehn (Edinburgh)
Title: Linguistic Problems for Statistical Machine Translation
Date: Wednesday 12 December 2007
Time: 14:00
Location: P.327, Euclides building, Plantage Muidergracht 24, Amsterdam

Machine translation is more relevant than ever, especially in a European Union with 23 official languages. What will happen to languages such as Dutch? Will it survive as a language of commerce, or will it be abandoned in favour of English? By lowering translation costs, we would expect to systain the viability of a commercial zone that uses so many different languages. Statistical machine translation holds the promise of instant machine translation. Given open source tools such the Moses decoder, just add a parallel corpus and you have a machine translation system. This talk will present some problems where the standard phrase-based approach fails, and where attention to the specifics of the languages involved is required. I will present methods that deal with different word order, morphology and agglutinative compounding.

For more information and abstracts, see http://www.illc.uva.nl/LaCo/CLS/

Please note that this newsitem has been archived, and may contain outdated information or links.