We propose a probabilistic network model, called asynchronous bounded expected delay (ABE), which requires a known bound on the expected message delay. In ABE networks all asynchr...
This paper proposes a novel Bayesian approximation inference method for mixture modeling. Our key idea is to factorize marginal log-likelihood using a variational distribution ove...
We present a new open source toolkit for phrase-based and syntax-based machine translation. The toolkit supports several state-of-the-art models developed in statistical machine t...
Mobile phones are set to become the universal interface to online services and cloud computing applications. However, using them for this purpose today is limited to two configura...
Ioana Giurgiu, Oriana Riva, Dejan Juric, Ivan Kriv...
With the rapidly falling price of hardware, and increasingly available bandwidth, the storage technology is seeing a paradigm shift from centralized and managed mode to distribute...