Developers have built many eGovernment applications using local ontologies to provide a meta-data description of what their service does, how it works, and how to invoke it. Every day more ontologies are written by different developers and posted on web servers around the world. Consequently, effective bridging of semantic web applications for eGovernment is challenging. This paper briefly desc...

Assigning semantic roles to the constituents of a natural language sentence is an important first step in translating natural language into a logical form for further processing. I present a statistical classifier which can perform this task using minimal syntactic cues. I use the syntactic and the semantic head of each constituent as the only features and present simple rules for extracting th...

The task of translating data from one schema into another is usually performed with the help of information stating how the elements between two schemas correspond. Translation mechanisms can use this information in order to identify how instances of a source schema must be translated. We claim that a uniform matching approach, where instances of a source classes are always translated into the ...

A technique for building a three-dimensional description of a static scene from a spatiotemporal image is presented. This technique utilizes Homocentric Spherical Spatiotemporal Image (HSSI) analysis and makes allowances for camera rotation, which is a wider class of camera motion than that in ordinary spatiotemporal image analysis. Experiments with real images from a translating and rotating c...

Two Visual Servoing controls respectively of the Position Based and Image Based type have been developed to govern a parallel translating manipulator with an eye-in-hand configuration. The robot must be able to reach and grasp a special target randomly positioned in the workspace; the control must be adaptive to compensate motions of the target in the 3D space. The implemented trajectory planni...

The rule based approach to machine translation (MT) confines grammatical rules between the source and the target language with the goal of constructing grammatical translation between the language pair. In this paper, we describe the structural representation of English stemmer, POS tagging and design transfer rules which can generate Hindi sentence from the structural representation of the Eng...

This paper describes a decoding algorithm for statistical machine translation based on phrases. In the past, the solution to the decoding problem were inspired from that of speech recognizers, translating each input word into one or more output words generating in left-to-right direction. The algorithm presented here iteratively constructs phrases or chunks of cepts until all the input words ar...

This paper presents an approach to translating Chinese organization names into English based on correlative expansion. Firstly, some candidate translations are generated by using statistical translation method. And several correlative named entities for the input are retrieved from a correlative named entity list. Secondly, three kinds of expansion methods are used to generate some expanded que...

Two different visual servoing controls have been developed to govern a translating parallel manipulator with an eye-in-hand configuration, That is, a position-based and an image-based controller. The robot must be able to reach and grasp a target randomly positioned in the workspace; the control must be adaptive to compensate motions of the target in the 3D space. The trajectory planning strate...

A low precision deep neural network training technique for producing sparse, ternary neural networks is presented. The technique incorporates hardware implementation costs during training to achieve significant model compression for inference. Training involves three stages: network training using L2 regularization and a quantization threshold regularizer, quantization pruning, and finally retr...