Smoothing and compression with stochastic k-testable tree languages

Please use this identifier to cite or link to this item:
Información del item - Informació de l'item - Item information
Title: Smoothing and compression with stochastic k-testable tree languages
Authors: Rico-Juan, Juan Ramón | Calera Rubio, Jorge | Carrasco, Rafael C.
Research Group/s: Transducens
Center, Department or Service: Universidad de Alicante. Departamento de Lenguajes y Sistemas Informáticos
Keywords: Tree grammars | Stochastic models | Ssmoothing | Backing-off | Data compression
Knowledge Area: Lenguajes y Sistemas Informáticos
Issue Date: 2-Apr-2005
Publisher: Elsevier
Citation: RICO JUAN, Juan Ramón; CALERA RUBIO, Jorge; CARRASCO JIMÉNEZ, Rafael Carlos. "Smoothing and compression with stochastic k-testable tree languages". Pattern Recognition. Vol. 38, No. 9 (Sept. 2005). ISSN 0031-3203, pp. 1420-1430
Abstract: In this paper, we describe some techniques to learn probabilistic k-testable tree models, a generalization of the well known k-gram models, that can be used to compress or classify structured data. These models are easy to infer from samples and allow for incremental updates. Moreover, as shown here, backing-off schemes can be defined to solve data sparseness, a problem that often arises when using trees to represent the data. These features make them suitable to compress structured data files at a better rate than string-based methods.
Sponsor: The Spanish Comisión Interministerial de Ciencia y Tecnología through Grants TIC2003-08681-C02 and TIC2003-08496-C04.
ISSN: 0031-3203 (Print) | 1873-5142 (Online)
DOI: 10.1016/j.patcog.2004.03.024
Language: eng
Type: info:eu-repo/semantics/article
Peer Review: si
Publisher version:
Appears in Collections:INV - TRANSDUCENS - Artículos de Revistas

Files in This Item:
Files in This Item:
File Description SizeFormat 
Thumbnailpr04.pdfPreprint (acceso libre)215,85 kBAdobe PDFOpen Preview
Thumbnailsmoothing_compression.pdfVersión final (acceso restringido)393,6 kBAdobe PDFOpen    Request a copy

Items in RUA are protected by copyright, with all rights reserved, unless otherwise indicated.