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-...
Deterministic dependency parsing has often been regarded as an efficient parsing algorithm while its parsing accuracy is a little lower than the best results reported by more comp...
Abstract--Generative models are created to be used in the design and performance assessment of high layer wireless communication protocols and some error control strategies. Genera...
Omar S. Salih, Cheng-Xiang Wang, David I. Laurenso...
We present a natural language interface system which is based entirely on trained statistical models. The system consists of three stages of processing: parsing, semantic interpre...
Scott Miller, David Stallard, Robert J. Bobrow, Ri...
In this paper we describe and evaluate several statistical models for the task of realization ranking, i.e. the problem of discriminating between competing surface realizations ge...