uu.seUppsala University Publications
Change search
ReferencesLink to record
Permanent link

Direct link
Character-based PSMT for Closely Related Languages
2009 (English)In: Proceedings of 13th Annual Conference of the European Association for Machine Translation (EAMT’09), 2009, 12-19 p.Conference paper (Refereed)
Abstract [en]

Translating unknown words between related languages using a character-based statistical machine translation model can be beneficial. In this paper, we describe a simple method to combine character-based models with standard word-based models to increase the coverage of a phrase-based SMT system. Using this approach, we can show a modest improvement when translating between Norwegian and Swedish. The potentials of applying character-based models to closely related languages is also illustrated by applying the character model on its own. The performance of such an approach is similar to the word-level baseline and closer to the reference in terms of string similarity.

Place, publisher, year, edition, pages
2009. 12-19 p.
National Category
Language Technology (Computational Linguistics)
Research subject
Computational Linguistics
URN: urn:nbn:se:uu:diva-165940OAI: oai:DiVA.org:uu-165940DiVA: diva2:474916
European Association for Machine Translation (EAMT)
Available from: 2012-01-10 Created: 2012-01-10 Last updated: 2014-01-09

Open Access in DiVA

No full text

Search in DiVA

By author/editor
Tiedemann, Jörg
Language Technology (Computational Linguistics)

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 156 hits
ReferencesLink to record
Permanent link

Direct link