We present a novel paradigm for statistical machine translation (SMT), based on a joint modeling of word alignment and the topical aspects underlying bilingual document-pairs, via...
Many tasks in speech processing involve classification of long term characteristics of a speech segment such as language, speaker, dialect, or topic. A natural technique for dete...
Adaptation to other initially unknown agents often requires computing an effective counter-strategy. In the Bayesian paradigm, one must find a good counterstrategy to the inferre...
Michael Johanson, Martin Zinkevich, Michael H. Bow...
Unsupervised learning algorithms aim to discover the structure hidden in the data, and to learn representations that are more suitable as input to a supervised machine than the ra...
In online handwriting recognition the trajectory of the pen is recorded during writing. Although the trajectory provides a compact and complete representation of the written outpu...