We investigate a simple semi-naive Bayesian ranking method that combines naive Bayes with induction of decision tables. Naive Bayes and decision tables can both be trained efficie...
We present a neural-network-based statistical parser, trained and tested on the Penn Treebank. The neural network is used to estimate the parameters of a generative model of left-...
We introduce variant types and a pattern matching operation to synchronous dataflow languages. These languages are used in the design of reactive systems. As these systems grow in...
This article presents the design of a new functional 2D image segmentation algorithm by cell merging in a subdivision, its proof of total correctness, and the derivation of an opt...
The core-adjunct argument distinction is a basic one in the theory of argument structure. The task of distinguishing between the two has strong relations to various basic NLP task...