This work investigates supervised word alignment methods that exploit inversion transduction grammar (ITG) constraints. We consider maximum margin and conditional likelihood objec...
Aria Haghighi, John Blitzer, John DeNero, Dan Klei...
The goal of online failure prediction is to forecast imminent failures while the system is running. This paper compares Similar Events Prediction (SEP) with two other well-known t...
We present the bubble cursor ? a new target acquisition technique based on area cursors. The bubble cursor improves upon area cursors by dynamically resizing its activation area d...
Predicting the interests of a user in information is an important process in personalized information systems. In this paper, we present a way to create prediction engines that al...
Mark van Setten, Mettina Veenstra, Anton Nijholt, ...
Speech enhancement is a common approach to address the effects of degradation due to noise and channel contamination. This approach is intended to suppress unwanted signal and rec...