This work explores neural approximation for nonlinear dimensionality reduction mapping based on internal representations of graph-organized regular data supports. Given training observations are assumed as a sample from high-dimensional space with an embedding low-dimensional manifold. An approximating function consisting adaptable built-in parameters is optimized subject to given by the propos...

LEMPAS, the lemmatizer for the Swedish corpus PAROLE, came into existence as a by-product of running the Sketch Engine (Kilgarrif et al., 2004) on Swedish, since many of the desirable features of the Sketch Engine, such as building word sketches, are only available for lemmatized corpora. We did not have access to any Swedish lexical sources and the time allowed for the lemmatization was very l...

In this paper we present the development of the terminology extraction module for Slovene which was framed within the Sketch Engine corpus management system and motivated by the KAS research project on resources and tools for analysing academic Slovene. We describe the formalism used for defining the grammaticality of terms as well as the calculation of the score of individual terms, give an ov...

This paper describes preliminary work with radiophosphorus (P-32) undertaken by the author at the S.A.S.A. Experiment Station, Mount Edgecombe. In order to study the root spread of N :Co.376, radiophosphorus in solution was injected into the soil at various distances, positions and depths in relation to the cane row. (Cane planted 3rd October, 1962.) Uptake of this radiophosphorus by the plant ...

We describe a system for taking a 2D sketch of a mirror-symmetric 3D shape and lifting the curves to 3D, inferring the symmetry relationship from the original hand-drawn curves. The system takes as input a hand-drawn sketch and generates a set of 3D curves such that their orthogonal projection matches the input sketch. The main contribution is a method which is able to identify the symmetry rel...

We proposes a language resource by automatically sketching grammatical relations of words based on dependency parses from untagged texts. The advantage of word sketch based on parsed corpora is, compared to Sketch Engine (Kilgarriff, Rychly, Smrz, & Tugwell, 2004), to provide more details about the different usage of each word such as various types of modification, which is also important in la...

We give a method to obtain a 3D CSG model from a 2D engineering wireframe sketch which depicts a polyhedral shape. The method finds a CSG feature tree compatible with a reverse design history of a 2D line-drawing obtained by vectorising the sketch. The process used seeks the CSG feature tree recursively, combining all design or manufacturing features embedded in the sketch, proceeding in revers...