We present a statistical generative model for unsupervised learning of verb argument structures. The model was used to automatically induce the argument structures for the 1,500 mo...
Thiago Alexandre Salgueiro Pardo, Daniel Marcu, Ma...
Pipeline computation, in which a task is decomposed into several stages that are solved sequentially, is a common computational strategy in natural language processing. The key pr...
: The semantics of the OR-join have been discussed for some time, in the context of EPCs, but also in the context of other business process modeling languages like YAWL. In this pa...
It is traditionally assumed that various sources of linguistic knowledge and their interaction should be formalised in order to be able to convert words into their phonemic repres...
This paper presents the design and evaluation of a text categorization method based on the Hierarchical Mixture of Experts model. This model uses a divide and conquer principle to ...