The standard approach to the classification of objects is to consider the examples as independent and identically distributed (iid). In many real world settings, however, this ass...
Almost all Chinese language processing tasks involve word segmentation of the language input as their first steps, thus robust and reliable segmentation techniques are always requ...
This paper presents a shallow dialogue analysis model, aimed at human-human dialogues in the context of staff or business meetings. Four components of the model are defined, and ...
Andrei Popescu-Belis, Alexander Clark, Maria Georg...
Abstract. For every segmentation task, prior knowledge about the object that shall be segmented has to be incorporated. This is typically performed either automatically by using la...
Margret Keuper, Robert Bensch, Karsten Voigt, Alex...
A number of recent systems for unsupervised featurebased learning of object models take advantage of cooccurrence: broadly, they search for clusters of discriminative features tha...