Using collocation segmentation to extract translation units in a phrase-based statistical machine translation system
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10045/14717
Title: | Using collocation segmentation to extract translation units in a phrase-based statistical machine translation system |
---|---|
Other Titles: | Implementación de una segmentación estadística complementaria para extraer unidades de traducción en un sistema de traducción estadístico basado en frases |
Authors: | Ruiz Costa-Jussà, Marta | Daudaravicius, Vidas | Banchs Martínez, Rafael Enrique |
Keywords: | Traducción automática | Segmentación | Machine translation | Collocation segmentation |
Knowledge Area: | Lenguajes y Sistemas Informáticos |
Issue Date: | Oct-2010 |
Publisher: | Sociedad Española para el Procesamiento del Lenguaje Natural |
Citation: | RUIZ COSTA-JUSSÀ, Marta; DAUDARAVICIUS, Vidas; BANCHS MARTÍNEZ, Rafael Enrique. “Using collocation segmentation to extract translation units in a phrase-based statistical machine translation system”. Procesamiento del Lenguaje Natural. N. 45 (2010). ISSN 1135-5948 |
Abstract: | Este artículo evalúa un nuevo método de segmentación en un sistema de traducción automática estadístico basado en frases. La técnica de segmentación se implementa tanto en la parte fuente como en la parte destino y se usa para extraer unidades de traducción. Los resultados mejoran el sistema de referencia en la tarea español-inglés del EuroParl. | This report evaluates the impact of using a novel collocation segmentation method for phrase extraction in the standard phrase-based statistical machine translation approach. The collocation segmentation technique is implemented simultaneously in the source and target side. The resulting collocation segmentation is used to extract translation units. Experiments are reported in the Spanish-to-English EuroParl task and promising results are achieved in translation quality. |
Sponsor: | This work has been partially funded by the Spanish Department of Education and Science through the Juan de la Cierva fellowship program. The authors also wants to thank the Barcelona Media Innovation Centre for its support and permission to publish this research. |
URI: | http://hdl.handle.net/10045/14717 |
ISSN: | 1135-5948 |
Language: | eng |
Type: | info:eu-repo/semantics/article |
Peer Review: | si |
Appears in Collections: | Procesamiento del Lenguaje Natural - Nº 45 (2010) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
PLN_45_16.pdf | 262,08 kB | Adobe PDF | Open Preview | |
Items in RUA are protected by copyright, with all rights reserved, unless otherwise indicated.