| |
|
|
 | Acesso ao texto completo restrito à biblioteca da Embrapa Meio Ambiente. Para informações adicionais entre em contato com cnpma.biblioteca@embrapa.br. |
|
Registro Completo |
|
Biblioteca(s): |
Embrapa Meio Ambiente. |
|
Data corrente: |
29/06/2012 |
|
Data da última atualização: |
05/01/2023 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Autoria: |
PRADO, H. A. do; FERNEDA, E.; RODRIGUES, F. C. da L.; MARTINS, E. de S.; CARVALHO JUNIOR, O. A. de; LUIZ, A. J. B. |
|
Afiliação: |
HERCULES ANTONIO DO PRADO, SGE; EDILSON FERNEDA, UNIVERSIDADE CATÓLICA DE BRASÍLIA; FRANCISCO CARLOS DA LUZ RODRIGUES, UNIVERSIDADE CATÓLICA DE BRASÍLIA; EDER DE SOUZA MARTINS, CPAC; OSMAR ABÍLIO DE CARVALHO JUNIOR, UNB; ALFREDO JOSE BARRETO LUIZ, CNPMA. |
|
Título: |
Structuring taxonomies from texts: a case-study on defining soil classes. |
|
Ano de publicação: |
2012 |
|
Fonte/Imprenta: |
Lecture Notes in Computer Science, Berlin, v. 7335, p. 657-666, 2012. |
|
Idioma: |
Inglês |
|
Conteúdo: |
Currently, most of the information digitally available is presented in textual form and it is largely acknowledged that, in many fields, the advance of knowledge may strongly benefit from this source of information. The treatment of this vast amount of texts by means of Text Mining (TM) techniques has produced interesting information in fields like Competitive Intelligence and Bibliometry that need to make sense from textual descriptions of facts. In this paper we approach the problem of taxonomy generation from texts, a common need from a large set of scientific disciplines. Taxonomy generation refers to building a hierarchical structure that organizes concepts in a knowledge domain. We applied TM techniques to help experts in Pedology in building taxonomy from redundant soils descriptions. The motto of the application is the fact that, in the early eighties, different organizations mapped and described equivalent classes of soils from Brazilian savannas, generating redundant descriptions with different class labels. There were produced 28 soil maps that covered 4,101 descriptions of soil classes. This profusion of redundant soil descriptions clearly represents a Babel Tower that makes difficult tasks like environment management and food production. The proposed process is based in clustering analysis and runs on the soil descriptions, performing a successive refinement of the abstractions found in soil descriptions. The method builds a frame that shows, for each cluster formed, the prototype (a representative word vector) and the soil descriptions related to that cluster. The results have been analyzed by a team of experts as input information to the laborious reasoning process involved in building concepts from the semantic relations among the soil descriptions. Without a help like the present process, the experts would have to compare visually at least 4,101 × 4.100 × ?× 1 soil descriptions to define the clusters, what is much more laborious. MenosCurrently, most of the information digitally available is presented in textual form and it is largely acknowledged that, in many fields, the advance of knowledge may strongly benefit from this source of information. The treatment of this vast amount of texts by means of Text Mining (TM) techniques has produced interesting information in fields like Competitive Intelligence and Bibliometry that need to make sense from textual descriptions of facts. In this paper we approach the problem of taxonomy generation from texts, a common need from a large set of scientific disciplines. Taxonomy generation refers to building a hierarchical structure that organizes concepts in a knowledge domain. We applied TM techniques to help experts in Pedology in building taxonomy from redundant soils descriptions. The motto of the application is the fact that, in the early eighties, different organizations mapped and described equivalent classes of soils from Brazilian savannas, generating redundant descriptions with different class labels. There were produced 28 soil maps that covered 4,101 descriptions of soil classes. This profusion of redundant soil descriptions clearly represents a Babel Tower that makes difficult tasks like environment management and food production. The proposed process is based in clustering analysis and runs on the soil descriptions, performing a successive refinement of the abstractions found in soil descriptions. The method builds a frame that shows, for each cluster fo... Mostrar Tudo |
|
Palavras-Chave: |
Mineração de texto; Text mining. |
|
Thesagro: |
Cerrado; Solo; Taxonomia. |
|
Thesaurus Nal: |
Soil taxonomy. |
|
Categoria do assunto: |
P Recursos Naturais, Ciências Ambientais e da Terra |
|
Marc: |
LEADER 02714naa a2200253 a 4500
001 1927451
005 2023-01-05
008 2012 bl uuuu u00u1 u #d
100 1 $aPRADO, H. A. do
245 $aStructuring taxonomies from texts$ba case-study on defining soil classes.$h[electronic resource]
260 $c2012
520 $aCurrently, most of the information digitally available is presented in textual form and it is largely acknowledged that, in many fields, the advance of knowledge may strongly benefit from this source of information. The treatment of this vast amount of texts by means of Text Mining (TM) techniques has produced interesting information in fields like Competitive Intelligence and Bibliometry that need to make sense from textual descriptions of facts. In this paper we approach the problem of taxonomy generation from texts, a common need from a large set of scientific disciplines. Taxonomy generation refers to building a hierarchical structure that organizes concepts in a knowledge domain. We applied TM techniques to help experts in Pedology in building taxonomy from redundant soils descriptions. The motto of the application is the fact that, in the early eighties, different organizations mapped and described equivalent classes of soils from Brazilian savannas, generating redundant descriptions with different class labels. There were produced 28 soil maps that covered 4,101 descriptions of soil classes. This profusion of redundant soil descriptions clearly represents a Babel Tower that makes difficult tasks like environment management and food production. The proposed process is based in clustering analysis and runs on the soil descriptions, performing a successive refinement of the abstractions found in soil descriptions. The method builds a frame that shows, for each cluster formed, the prototype (a representative word vector) and the soil descriptions related to that cluster. The results have been analyzed by a team of experts as input information to the laborious reasoning process involved in building concepts from the semantic relations among the soil descriptions. Without a help like the present process, the experts would have to compare visually at least 4,101 × 4.100 × ?× 1 soil descriptions to define the clusters, what is much more laborious.
650 $aSoil taxonomy
650 $aCerrado
650 $aSolo
650 $aTaxonomia
653 $aMineração de texto
653 $aText mining
700 1 $aFERNEDA, E.
700 1 $aRODRIGUES, F. C. da L.
700 1 $aMARTINS, E. de S.
700 1 $aCARVALHO JUNIOR, O. A. de
700 1 $aLUIZ, A. J. B.
773 $tLecture Notes in Computer Science, Berlin$gv. 7335, p. 657-666, 2012.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Meio Ambiente (CNPMA) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
|
| Registros recuperados : 9 | |
| 1. |  | FILIPPINI ALBA, J. M.; SOUZA FILHO, C. R. de. GIS-based environmental risk assessment in the Ribeira Valley, São Paulo, Brazil. Environmental Earth Sciences, v. 59, n. 5, p. 1139-1147, jan, 2010,| Tipo: Artigo em Periódico Indexado | Circulação/Nível: B - 1 |
| Biblioteca(s): Embrapa Clima Temperado. |
|    |
| 5. | | LUIZ, A. J. B.; MAIA, A. de H. N.; SANCHES, I. D. A.; GÜRTLER, S.; SOUZA FILHO, C. R. de. Busca de relações quando o número de variáveis é muito maior que o de observações: o caso de dados hiperespectrais. In: REUNIÃO ANUAL DA REGIÃO BRASILEIRA DA SOCIEDADE INTERNACIONAL DE BIOMETRIA, 60.; SIMPÓSIO DE ESTATÍSTICA APLICADA À EXPERIMENTAÇÃO AGRONÔMICA, 16., 2015, Presidente Prudente. A estatística e os novos desafios: tratamento e modelagem da informação: anais... Presidente Prudente: Sociedade Internacional de Biometria, 2015. 10 p.| Tipo: Artigo em Anais de Congresso |
| Biblioteca(s): Embrapa Meio Ambiente. |
| |
| 7. | | FRANCESCHINI, M. H. D.; DEMATTÊ, J. A. M.; TERRA, F. DA S.; ARAÚJO, S. R.; SOUZA FILHO, C. R. DE; VICENTE, L. E. Qualificação de atributos físico-químicos do solo através de dados espectrais (Vis-NIR-SWIR) obtidos em laboratório e por imagem aérea hiperespectral. In: SIMPÓSIO BRASILEIRO DE SENSORIAMENTO REMOTO, 16., 2013, Foz do Iguaçú. Anais... São José dos Campos: INPE, 2013. p.0530-0538 1 CD-ROM| Tipo: Artigo em Anais de Congresso |
| Biblioteca(s): Embrapa Territorial. |
| |
| 8. | | VASQUES, G. M.; DEMATTÊ, J. A. M.; VISCARRA ROSSEL, R. A.; RAMÍREZ LÓPEZ, S.; TERRA, F. S.; RIZZO, R.; SOUZA FILHO, C. R. de. Integrating geospatial and multi-depth laboratory spectral data for mapping soil classes in a geologically complex area in southeastern Brazil. European Journal of Soil Science, v. 66, n. 4, p. 767-779, Jul. 2015.| Tipo: Artigo em Periódico Indexado | Circulação/Nível: A - 1 |
| Biblioteca(s): Embrapa Solos. |
|  |
| 9. | | OLIVEIRA, D. P. de; PULIDO, J.; FRANCHESCHINI, M. H. D.; COSTA, P. A. da; ARRUDA, G. P. de; DEMATTÊ, J. A. M.; SOUZA FILHO, C. R. de; VICENTE, L. E. Caracterização espectral de solos utilizando espectrorradiômetro em laboratório e imagem de satélite hiperespectral. In: SIMPÓSIO BRASILEIRO DE SENSORIAMENTO REMOTO, 15., 2011, Curitiba. Anais... São José dos Campos: INPE, 2011. p. 8476-8483.| Tipo: Artigo em Anais de Congresso |
| Biblioteca(s): Embrapa Territorial. |
| |
| Registros recuperados : 9 | |
|
| Nenhum registro encontrado para a expressão de busca informada. |
|
|
