We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedu...
In the context of Model Driven Development, models play a central role. Since models can nowadays be executed, they are used not only for description but also for production [32][3...
In this paper, we introduce a method that automatically builds text classifiers in a new language by training on already labeled data in another language. Our method transfers the...
We propose a method for providing stochastic confidence estimates for rule-based and black-box natural language (NL) processing systems. Our method does not require labeled trainin...
Christian Monson, Kristy Hollingshead, Brian Roark
We propose the Arabic Chat Alphabet (ACA) as naturally written in everyday life for dialectal Arabic speech transcription. Our assumption is that ACA is a natural language that in...