We propose three new features for MT evaluation: source-sentence constrained n-gram precision, source-sentence reordering metrics, and discriminative unigram precision, as well as...
Maximum entropy models are a common modeling technique, but prone to overfitting. We show that using an exponential distribution as a prior leads to bounded absolute discounting b...
Abstract--We present a method for improving existing statistical machine translation methods using an knowledge-base compiled from a bilingual corpus as well as sequence alignment ...
To learn concepts over massive data streams, it is essential to design inference and learning methods that operate in real time with limited memory. Online learning methods such a...
The focus of my thesis is on the development of a multi-method framework for the validation of formal models (domain model, user model, and teaching model) for adaptive work-integr...