Current re-ranking algorithms for machine translation rely on log-linear models, which have the potential problem of underfitting the training data. We present BoostedMERT, a nove...
Active systems are emerging in many fields, being particularly interesting those like Active Database Management Systems which always provide some kind of reactive capabilities. I...
Predictive user models often require a phase of effortful supervised training where cases are tagged with labels that represent the status of unobservable variables. We formulate a...
Abstract. This paper describes the process by which we are constructing an intelligent tutoring system (ERST) designed to improve learners’ external representation (ER) selection...
Abstract. This paper presents our recent work on period disambiguation, the kernel problem in sentence boundary identification, with the maximum entropy (Maxent) model. A number o...