Brain-computer interfaces rely on accurate decoding of cortical activity to understand intended action. Algorithms for neural decoding can be broadly categorized into two groups: d...
Hierarchical phrase-based models provide a powerful mechanism to capture non-local phrase reorderings for statistical machine translation (SMT). However, many phrase reorderings a...
This paper presents a novel online relevant set algorithm for a linearly-scored block sequence translation model. The key component is a new procedure to directly optimize the glob...
Syntactic analysis influences the way in which the source sentence is translated. Previous efforts add syntactic constraints to phrase-based translation by directly rewarding/puni...
In this paper, we present a novel approach to enhance hierarchical phrase-based machine translation systems with linguistically motivated syntactic features. Rather than directly ...