This paper presents a direct word reordering model with novel syntax-based features for statistical machine translation. Reordering models address the problem of reordering source...
In this paper we propose a new motion compensated prediction technique that enables successful predictive encoding during fades, blended scenes, temporally decorrelated noise, and...
In competitive domains, the knowledge about the opponent can give players a clear advantage. This idea lead us in the past to propose an approach to acquire models of opponents, ba...
In recent work we showed that models constructed from planner performance data over a large suite of benchmark problems are surprisingly accurate; 91-99% accuracy for success and ...
Mark Roberts, Adele E. Howe, Brandon Wilson, Marie...
There is an increasing interest in more accurate prediction of software maintainability in order to better manage and control software maintenance. Recently, TreeNet has been prop...