International Workshop on Spoken Language Translation (IWSLT) 2006
Keihanna Science City, Kyoto, Japan
Currently most statistical machine translation systems make use of alignments as a first step in the process of training the actual translation models. Several researchers have investigated how to improve the alignment quality, with the (intuitive) assumption that better alignments increase the translation quality. In this paper we will investigate this assumption and show that this is not always the case.
Full Paper Presentation
Bibliographic reference. Vilar, David / Popović, Maja / Ney, Hermann (2006): "AER: do we need to improve our alignments?", In IWSLT-2006, 205-212.