The impact of morphological errors in phrase-based statistical machine translation from German and English into Swedish
Number of Authors: 1
2009 (English)Conference paper (Refereed)
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.
Computer and Information Science
IdentifiersURN: urn:nbn:se:ri:diva-15929OAI: oai:DiVA.org:ri-15929DiVA: diva2:1037953
4th Language & Technology Conference