This paper presents a novel training algorithm for a linearly-scored block sequence translation model. The key component is a new procedure to directly optimize the global scoring...
We propose a scheme for modeling point sample geometry with statistical analysis. In our scheme we depart from the current schemes that deterministically represent the attributes ...
This paper demonstrates how unsupervised techniques can be used to learn models of deep linguistic structure. Determining the semantic roles of a verb's dependents is an impo...
— When analyzed in the tangential speed domain, human movements exhibit a multi-peaked speed profile which is commonly interpreted as evidence for submovements. At slow speeds, ...
An efficient decoding algorithm is a crucial element of any statistical machine translation system. Some researchers have noted certain similarities between SMT decoding and the f...
Mikhail Zaslavskiy, Marc Dymetman, Nicola Cancedda