ScaleMT: a free/open-source framework for building scalable machine translation web services

Por favor, use este identificador para citar o enlazar este ítem: http://hdl.handle.net/10045/14267
Información del item - Informació de l'item - Item information
Título: ScaleMT: a free/open-source framework for building scalable machine translation web services
Autor/es: Sánchez-Cartagena, Víctor M. | Pérez-Ortiz, Juan Antonio
Grupo/s de investigación o GITE: Transducens
Centro, Departamento o Servicio: Universidad de Alicante. Departamento de Lenguajes y Sistemas Informáticos
Palabras clave: High scalability | Machine translation | Apertium | Web services
Área/s de conocimiento: Lenguajes y Sistemas Informáticos
Fecha de creación: dic-2009
Fecha de publicación: ene-2010
Editor: Charles University in Prague. Institute of Formal and Applied Linguistics | Versita
Cita bibliográfica: SÁNCHEZ-CARTAGENA, Víctor M.; PÉREZ-ORTIZ, Juan Antonio. "ScaleMT: a free/open-source framework for building scalable machine translation web services". The Prague Bulletin of Mathematical Linguistics. No. 93 (Jan. 2010). ISSN 0032-6585, pp. 97-106
Resumen: Machine translation web services usage is growing amazingly mainly because of the translation quality and reliability of the service provided by the Google Ajax Language API. To allow the open-source machine ranslation projects to compete with Google’s one and gain visibility on the internet, we have developed ScaleMT: a free/open-source framework that exposes existing machine translation engines as public web services. This framework is highly scalable as it can run coordinately on many servers, fficiently managing the resources needed by the engines, and its API is compatible with Google’s one. ScaleMT is based on previous efforts to build a web service for the Apertium machine translation toolbox, but we have also tested it with Matxin, another free/open-source transfer-based machine translation engine. Additionally, we have compared ScaleMT to an alternative web service implementation for Apertium, obtaining satisfactory results.
Patrocinador/es: This work has been partially funded by Google through the Google Summer of Code program and by Spanish Ministerio de Ciencia e Innovación through project TIN2009-14009-C02-01.
URI: http://hdl.handle.net/10045/14267
ISBN: 978-80-904175-4-0
ISSN: 0032-6585 (Print) | 1804-0462 (Online)
DOI: 10.2478/v10108-010-0011-9
Idioma: eng
Tipo: info:eu-repo/semantics/article
Revisión científica: si
Versión del editor: http://dx.doi.org/10.2478/v10108-010-0011-9
Aparece en las colecciones:INV - TRANSDUCENS - Artículos de Revistas

Archivos en este ítem:
Archivos en este ítem:
Archivo Descripción TamañoFormato 
Thumbnailmtmarathon2010-scalemt.pdf145,95 kBAdobe PDFAbrir Vista previa


Todos los documentos en RUA están protegidos por derechos de autor. Algunos derechos reservados.