Open Source Text Processing Project: MGIZA

MGIZA++: a multi-threaded word alignment tool based on GIZA++ Project Website: http://www.kyloo.net/software/doku.php/mgiza:overview Github Link: https://github.com/moses-smt/mgiza Description MGIZA++ is a multi-threaded word alignment tool based on GIZA++. It extends GIZA++ in multiple ways: Multi-threading MGIZA++ can make use of multi-core platforms … Continue reading

Open Source Text Processing Project: mkcls

mkcls: Training of word classes Project Website: http://www.fjoch.com/mkcls.html Github Link: https://github.com/moses-smt/giza-pp Description mkcls is a tool to train word classes by using a maximum-likelihood-criterion. The resulting word classes are especially suited for language models or statistical translation models. The program … Continue reading

Open Source Text Processing Project: GIZA++

GIZA++: Training of statistical translation models Project Website: http://www.fjoch.com/GIZA++.html Github Link: https://github.com/moses-smt/giza-pp Description GIZA++ is an extension of the program GIZA (part of the SMT toolkit EGYPT) which was developed by the Statistical Machine Translation team during the summer workshop … Continue reading