In this work, a new approach to vocabulary reduction is presented. It is based on filtering words in the topic feature space instead of directly in the original word space. The main goal is to analyze the differences between the application of the Cumulative Count-based word filter (fcc) in word feature space (BoW: Bag of Words) with respect to its application in topic descriptions (obtained by...

Many important well-known constants such as π and ζ(3) can be approximated by a truncated hypergeometric series. A modular algorithm based on rational number reconstruction was previously proposed to reduce space complexity of the well-known binary splitting algorithm [1]. In this paper, we examine some variations of this algorithm using Mersenne number moduli and Montgomery multiplication. Imp...

INTRODUCTION TO PLANT PATHOLOGY. New second edition By FREERICK DEFOREST HFEALD, Professor Emeritus of Plant Pathology, The State College of Washington. McGraw-Hill Publications in the Agricultural Sciences. 603 pages, 6 x 9, 246 illustrations, $4.00 In revising this well-known text, the author has retained his general plan of presenting a rounded, detailed introduction, in which the significan...

Implementing rules, constraints, and requirements contained in regulatory documents such as standards or guidelines constitutes a mandatory task for organizations and institutions across several domains. Due to the amount of domain-specific information and actions encoded in these documents, organizations often need to establish cooperations between several departments and consulting experts to...

This article presents a general method to use information retrieved from the Latent Dirichlet Allocation (LDA) topic model for Text Segmentation: Using topic assignments instead of words in two well-known Text Segmentation algorithms, namely TextTiling and C99, leads to significant improvements. Further, we introduce our own algorithm called TopicTiling, which is a simplified version of TextTil...

A graph is called n-existentially closed or n-e.c. if it satis/es the following adjacency property: for every n-element subset S of the vertices, and for every subset T of S, there is a vertex not in S which is joined to all of T and to none of S\T . The unique countable random graph is known to be n-e.c. for all n. Equivalently, for any /xed n, almost all /nite graphs are n-e.c. However, few e...

To select an adequate coding is one of the main problems in applications based on Evolutionary Algorithms. Many codings have been proposed to represent the search space for obtaining decision rules. A suitable representation of the individuals of the genetic population can reduce the search space, so that the learning process is accelerated by decreasing the number of necessary generations to c...

In this paper we address the automatic summarization task. Recent research works on extractive-summary generation employ some heuristics, but few works indicate how to select the relevant features. We will present a summarization procedure based on the application of trainable Machine Learning algorithms which employs a set of features extracted directly from the original text. These features a...

This paper proposes a calculational approach to prove properties of two well-known binary trees used to enumerate the rational numbers: the Stern-Brocot tree and the Eisenstein-Stern tree (also known as CalkinWilf tree). The calculational style of reasoning is enabled by a matrix formulation that is well-suited to naturally formulate path-based properties, since it provides a natural way to ref...

This paper presents a lyrics retrieval system called LyricsRadar that enables users to interactively browse song lyrics by visualizing their topics. Since conventional lyrics retrieval systems are based on simple word search, those systems often fail to reflect user’s intention behind a query when a word given as a query can be used in different contexts. For example, the word“tears”can appear ...