The thesis presents an attempt at using the syntactic structure in natural language for improved language models for speech recognition. The structured language model merges techniques in automatic parsing and language modeling using an original probabilistic parameterization of a shift-reduce parser. A maximum likelihood reestimation procedure belonging to the class of expectation-maximization...

Portable Standard LISP (PSL, Version 3.4) and REDUCE 3 were implemented for Cray 1 and Cray X-MP computers at the Konrad Zuse-Zentrum Berlin in 1986. As an special aspect of the implementation of PSL, an interface to the vector hardware of Cray processors was defined. With that interface and mostly driven by the needs of REDUCE applications (e.g. extensive calculations of Gröbner bases), the ar...

This paper suggests two ways of improving semantic role labeling (SRL). First, we introduce a novel transition-based SRL algorithm that gives a quite different approach to SRL. Our algorithm is inspired by shift-reduce parsing and brings the advantages of the transitionbased approach to SRL. Second, we present a self-learning clustering technique that effectively improves labeling accuracy in t...

Using standard calculus, explicit formulas for one-, twoand three-dimensional homotopy operators are presented. A derivation of the one-dimensional homotopy operator is given. A similar methodology can be used to derive the multi-dimensional versions. The calculus-based formulas for the homotopy operators are easy to implement in computer algebra systems such as Mathematica, Maple, and REDUCE. ...

in this paper, an algorithm , based on genetics and auxiliary nodes, to reduce energy consumption in wireless sensor networks has been presented. in this research, by considering some parameters as energy and distance, a target function has been created, which is more optimum comparing to other methods. in this research cluster head is selected by genetic algorithm. in rawsn algorithm a new tec...