We present a novel approach to natural language generation (NLG) that applies hierarchical reinforcement learning to text generation in the wayfinding domain. Our approach aims to...
Abstract. We are working on the construction of a Spanish-Basque (eseu) machine translation tool using the traditional transfer model based on shallow and dependency parsing. Spani...
We propose a novel unsupervised learning framework for activity perception. To understand activities in complicated scenes from visual data, we propose a hierarchical Bayesian mod...
Tolerances are a very important property of a design. This paper presents a method for simulating tolerances in signal processing and control systems on the system level using a...
Wilhelm Heupke, Christoph Grimm, Klaus Waldschmidt
We describe experiments with a Naive Bayes text classifier in the context of anti-spam E-mail filtering, using two different statistical event models: a multi-variate Bernoulli ...