Abstract One of the main hurdles to improved CLIR effectiveness is resolving ambiguity associated with translation. Availability of resources is also a problem. First we present a ...
For many years, statistical machine translation relied on generative models to provide bilingual word alignments. In 2005, several independent efforts showed that discriminative m...
Minimum Error Rate Training (MERT) and Minimum Bayes-Risk (MBR) decoding are used in most current state-of-theart Statistical Machine Translation (SMT) systems. The algorithms wer...
Shankar Kumar, Wolfgang Macherey, Chris Dyer, Fran...
Abstract. In automatic sign language translation, one of the main problems is the usage of spatial information in sign language and its proper representation and translation, e.g. ...
We present two methods for estimating replacement probabilities without using parallel corpora. The first method proposed exploits the possible translation probabilities latent in ...