Automatic induction of shallow-transfer rules for open-source machine translation

Please use this identifier to cite or link to this item:
Información del item - Informació de l'item - Item information
Title: Automatic induction of shallow-transfer rules for open-source machine translation
Authors: Sánchez-Martínez, Felipe | Forcada, Mikel L.
Research Group/s: Transducens
Center, Department or Service: Universidad de Alicante. Departamento de Lenguajes y Sistemas Informáticos
Keywords: Shallow-transfer rules | Open-source | Machine translation
Knowledge Area: Lenguajes y Sistemas Informáticos
Issue Date: 2007
Publisher: University of Skövde
Citation: SÁNCHEZ MARTÍNEZ, Felipe; FORCADA ZUBIZARRETA, Mikel L. "Automatic induction of shallow-transfer rules for open-source machine translation". En: TMI 2007 : proceedings of the 11th International Conference on Theoretical and Methodological Issues in Machine Translation, [Skövde, 7-9 September 2007] / Andy Way, Barbara Gawronska (eds.). Skövde : University of Skövde, 2007. (Skövde University studies in informatics; 2007:1). ISBN 978-91-977095-0-7, pp. 181-190
Abstract: This paper focuses on the inference of structural transfer rules for shallow-transfer machine translation (MT). Transfer rules are generated from alignment templates, like those used in statistical MT, that have been extracted from parallel corpora and extended with a set of restrictions that control their application. The experiments conducted using the open-source MT platform Apertium show that there is a clear improvement in translation quality as compared to word-for-word translation (when no transfer rules are used), and that the resulting translation quality is very close to the one obtained using hand-coded transfer rules. The method we present is entirely unsupervised and benefits from information in the rest of modules of the MT system in which the inferred rules are applied.
Sponsor: Spanish Government through projects TIC2003-08681-C02-01 and TIN2006-15071-C03-01. Spanish Government and the European Social Fund through research grant BES-2004-4711.
ISBN: 978-91-977095-0-7
ISSN: 1653-2325
Language: eng
Type: info:eu-repo/semantics/bookPart
Peer Review: si
Appears in Collections:INV - TRANSDUCENS - Comunicaciones a Congresos, Conferencias, etc.

Files in This Item:
Files in This Item:
File Description SizeFormat 
Thumbnailsanchez07c.pdfVersión de los autores118,21 kBAdobe PDFOpen Preview

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