Change search
ReferencesLink to record
Permanent link

Direct link
The impact of morphological errors in phrase-based statistical machine translation from German and English into Swedish
RISE, Swedish ICT, SICS. Userware.
Number of Authors: 1
2009 (English)Conference paper (Refereed)
Abstract [en]

We have investigated the potential for improvement in target language morphology when translating into Swedish from English and German, by measuring the errors made by a state of the art phrase-based statistical machine translation system. Our results show that there is indeed a performance gap to be filled by better modelling of inflectional morphology and compounding; and that the gap is not filled by simply feeding the translation system with more training data.

Place, publisher, year, edition, pages
Poznan, Poland, 2009, 8. 546-550 p.
National Category
Computer and Information Science
Identifiers
URN: urn:nbn:se:ri:diva-23614OAI: oai:DiVA.org:ri-23614DiVA: diva2:1042690
Conference
4th Language & Technology Conference
Available from: 2016-10-31 Created: 2016-10-31

Open Access in DiVA

fulltext(121 kB)3 downloads
File information
File name FULLTEXT01.pdfFile size 121 kBChecksum SHA-512
5ac628b454d571a6a8c326e61e0187f84ca7f8ae6e40aff306041eb12b54fad1c0cad60a388b7347f7c3e1f7226538b7c2a32fb875a5051fb3e9711d25d17b4f
Type fulltextMimetype application/pdf

By organisation
SICS
Computer and Information Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 3 downloads
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

ReferencesLink to record
Permanent link

Direct link