MOOD: A Modular Object-Oriented Decoder for Statistical Machine Translation
Alexandre Patry, Fabrizio Gotti, Philippe Langlais · 2006
We present an Open Source framework called MOOD developed in order to facilitate the development of a Statistical Machine Translation Decoder.MOOD has been modularized using an object-oriented approach which makes it especially suitable for the fast development of state-of-the-art decoders.As a proof of concept, a clone of the PHARAOH decoder has been implemented and evaluated.This clone named RAMSES is part of the current distribution of MOOD.