Joint learning and dictionary construction for pattern recognition

We propose a joint representation and classification framework that achieves the dual goal of finding the most discriminative sparse overcomplete encoding and optimal classifier parameters. Formulating an optimization problem that combines the objective function of the classification with the representation error of both labeled and unlabeled data, constrained by sparsity, we propose an algorithm that alternates between solving for subsets of parameters, whilst preserving the sparsity. The method is then evaluated over two important classification problems in computer vision: object categorization of natural images using the Caltech 101 database and face recognition using the Extended Yale B face database. The results show that the proposed method is competitive against other recently proposed sparse overcomplete counterparts and considerably outperforms many recently proposed face recognition techniques when the number training samples is small.

Sparse Representations of Image via Overcomplete Dictionary Learned by Adaptive Non-orthogonal Sparsifying Transform

How to learn an over complete dictionary for sparse representations of image is an important topic in machine learning, sparse coding, blind source separation, etc. The so-called K-singular value decomposition (K-SVD) method [3] is powerful for this purpose, however, it is too time-consuming to apply. Recently, an adaptive orthogonal sparsifying transform (AOST) method has been developed to learn the dictionary that is faster. However, the corresponding coefficient matrix may not be as sparse as that of K-SVD. For solving this problem, in this paper, a non-orthogonal iterative match method is proposed to learn the dictionary. By using the approach of sequentially extracting columns of the stacked image blocks, the non-orthogonal atoms of the dictionary are learned adaptively, and the resultant coefficient matrix is sparser. Experiment results show that the proposed method can yield effective dictionaries and the resulting image representation is sparser than AOST.

Garantia literária: elementos para uma revisão crítica após um século

This study contributes to a critical synthesis of the principle of literary warrant, initially formulated by Hulme in 1911. Hulme proposed that the terms of a classification system should be derived from the literature to be classified, rather than based on purely theoretical considerations. Founding literary warrant on literature which is actually documented rather than on scientific or philosophical classifications or on the supposed authority of the first classificationists implied a clear departure from the conceptions of Harris and Dewey, who had used the classifications of Bacon and Leibniz as models. The validity of this principle over the past century is studied by means of diverse documental data (entries in dictionaries, retrieval by Google, etc.), as it is recognized as a main methodological element for classification standards and systems. This study also discusses the situation with respect to the top-down or bottom-up methodologies of system design. Three traditional applications of literary warrant are described as well as three new applications are suggested, in light of its methodological potential. It is possible to conclude that this principle will find increasing applications in other contexts, within and beyond Information Science.

Correspondência idiomática intra e interlínguas

Este artigo aborda a questão da equivalência na tradução de expressões idiomáticas para a lexicografia bilíngüe. Considera­se que a fim de se alcançar uma equivalência idiomática o significado da palavra não é fixo nem estável e que se faz necessária uma pesquisa detalhada em vários dicionários bem como junto a informantes nativos.

Lexicografia pedagógica: atores e interfaces

Os dicionários para aprendizes de línguas estrangeiras são obras relativamente recentes no mercado editorial e atendem uma demanda por obras pedagógicas que foi ignorada pelos lexicógrafos durante muito tempo. Esse segmento do mercado lexicográfico vem se revelando promissor, com diversas possibilidades de inovações. A fim de delinear o campo de desenvolvimento da Lexicografia Pedagógica, este artigo analisa-a sob duas perspectivas: a de suas interfaces com outras áreas da Lingüística e a de seus atores, pessoas cuja atuação influencia a produção de suas obras. Esta exposição tem o objetivo de despertar o interesse de pesquisadores brasileiros pela Lexicografia Pedagógica e, indiretamente, promover a produção nacional de dicionários pedagógicos.

Reflexos da evolução do ensino de línguas na lexicografia bilíngüe

O dicionário bilíngüe e o aprendizado de línguas estrangeiras sempre estiveram associados. Este artigo procura evidenciar como o papel do dicionário bilíngüe foi se alterando com as mudanças no ensino de línguas estrangeiras e como isso pode estar relacionado ao movimento de evolução da lexicografia bilíngüe no sentido de tornar os dicionários mais adequados às necessidades dos aprendizes de línguas estrangeiras.

A variedade léxica da língua espanhola em dicionários bilíngues espanhol-português para aprendizes brasileiros

Due to factors such as globalization and the demography of Hispanic countries, the Spanish language has influenced worldwide, especially since the last decade of the 20th century, mainly countries which are geographically close to Spanish American countries, such as Brazil. In this context, it is necessary to think of the linguistic variation of the Spanish language, in which we emphasize the lexical variation. As any language, Spanish has a colossal and wealthy lexicon with different varieties related to the characteristics from each region: history, culture, customs etc. This diversity influences the development, the amplification and the renewal of a language, as well as the teaching-learning process. Thus, we proposed to analyze the lexicon varieties of Spanish language entries in some Spanish-Portuguese bilingual dictionaries for Brazilian learners. In order to achieve this goal, we selected some examples of lexical variety in a corpus organized with texts of different textual genres and we verified if these lexical items are registered in the dictionaries chosen. As the corpus is organized from texts present in didactic manuals used in Brazil, our goal is to verify if the vocabulary which the Brazilian learner has contact in formal education is registered in the analyzed dictionaries.

Image categorization through optimum path forest and visual words

Different from the first attempts to solve the image categorization problem (often based on global features), recently, several researchers have been tackling this research branch through a new vantage point - using features around locally invariant interest points and visual dictionaries. Although several advances have been done in the visual dictionaries literature in the past few years, a problem we still need to cope with is calculation of the number of representative words in the dictionary. Therefore, in this paper we introduce a new solution for automatically finding the number of visual words in an N-Way image categorization problem by means of supervised pattern classification based on optimum-path forest. © 2011 IEEE.

Automatic visual dictionary generation through Optimum-Path Forest clustering

Image categorization by means of bag of visual words has received increasing attention by the image processing and vision communities in the last years. In these approaches, each image is represented by invariant points of interest which are mapped to a Hilbert Space representing a visual dictionary which aims at comprising the most discriminative features in a set of images. Notwithstanding, the main problem of such approaches is to find a compact and representative dictionary. Finding such representative dictionary automatically with no user intervention is an even more difficult task. In this paper, we propose a method to automatically find such dictionary by employing a recent developed graph-based clustering algorithm called Optimum-Path Forest, which does not make any assumption about the visual dictionary's size and is more efficient and effective than the state-of-the-art techniques used for dictionary generation. © 2012 IEEE.

Terminologia de contratos de locação de imóveis: estudo terminológico bilíngue e elaboração de glossário Português-Francês

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Aspectos comparativos da regência verbal em Português e Inglês para a elaboração de um dicionário bilíngue

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Fraseologismos zoônimos: elaboração de base de dados Português-Francês

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Análise da adaptação de um dicionário bilíngue francês-português europeu para a variante brasileira

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Estudo sobre as expressões idiomáticas e o uso de dicionários especiais da língua portuguesa no ensino fundamental

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Proposta de modelo de dicionário bilíngue português-francês/francês-português de termos de estatutos sociais: uma colaboração para tradudores juramentados

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)