We consider an online learning scenario in which the learner can make predictions on the basis of a fixed set of experts. We derive upper and lower relative loss bounds for a cla...
Java is the canonical language for teaching introductory programming, but its complex syntax and abundance of constructs are difficult for beginners to learn. This paper shows how...
James I. Hsia, Elspeth Simpson, Daniel Smith, Robe...
In this paper, we describe design motivations and experience with a visual language that treats the architecture of a reactive system as a composition of small, asynchronous softw...
This paper explores the use of statistical machine translation (SMT) methods for tactical natural language generation. We present results on using phrase-based SMT for learning to...
In this paper we present some lessons learned from building vizsla, the keyword search and topic classification system used on the largest Hungarian portal, [origo.hu]. Based on ...