Alignment combination (symmetrization) has been shown to be useful for improving Machine Translation (MT) models. Most existing alignment combination techniques are based on heuri...
A Named Entity Recognizer (NER) generally has worse performance on machine translated text, because of the poor syntax of the MT output and other errors in the translation. As som...
This paper extends the training and tuning regime for phrase-based statistical machine translation to obtain fluent translations into morphologically complex languages (we build ...
We present a framework where auxiliary MT systems are used to provide lexical predictions to a main SMT system. In this work, predictions are obtained by means of pivoting via aux...
Recently, various synchronous grammars are proposed for syntax-based machine translation, e.g. synchronous context-free grammar and synchronous tree (sequence) substitution gramma...