We present a categorical theory of ‘well-behaved’ operational semantics which aims at complementing the established theory of domains and denotational semantics to form a cohe...
In this paper, we study the problem of automatically segmenting written text into paragraphs. This is inherently a sequence labeling problem, however, previous approaches ignore t...
Qinfeng Shi, Yasemin Altun, Alex J. Smola, S. V. N...
We investigate the recovery of signals exhibiting a sparse representation in a general (i.e., possibly redundant or incomplete) dictionary that are corrupted by additive noise adm...
Christoph Studer, Patrick Kuppinger, Graeme Pope, ...
Distance functions are an important component in many learning applications. However, the correct function is context dependent, therefore it is advantageous to learn a distance f...
In this paper, we present a new co-training strategy that makes use of unlabelled data. It trains two predictors in parallel, with each predictor labelling the unlabelled data for...