Background: Multiple genome alignment is an important problem in bioinformatics. An important subproblem used by many multiple alignment approaches is that of aligning two multipl...
We present a method to transliterate names in the framework of end-to-end statistical machine translation. The system is trained to learn when to transliterate. For Arabic to Engl...
Syntax-based translation models that operate on the output of a source-language parser have been shown to perform better if allowed to choose from a set of possible parses. In thi...
This paper studies transliteration alignment, its evaluation metrics and applications. We propose a new evaluation metric, alignment entropy, grounded on the information theory, t...
I describe two methods for incorporating information about the relative positions of bilingual word pairs into a Maximum Entropy/Minimum Divergence translation model. The better o...