Loading...
Loading...

Go to the content (press return)

N-gram-based machine translation

Author
Mariño, J.B.; Banchs, R.; Crego, J.; de Gispert, A.; Lambert, P.; Fonollosa, José A. R.; Ruiz, M.
Type of activity
Journal article
Journal
Computational linguistics
Date of publication
2006-12-01
Volume
32
Number
4
First page
527
Last page
549
DOI
https://doi.org/10.1162/coli.2006.32.4.527 Open in new window
Repository
http://hdl.handle.net/2117/117432 Open in new window
URL
http://www.mitpressjournals.org/doi/pdf/10.1162/coli.2006.32.4.527 Open in new window
Abstract
This article describes in detail an n-gram approach to statistical machine translation. This ap- proach consists of a log-linear combination of a translation model based on n-grams of bilingual units, which are referred to as tuples, along with four specific feature functions. Translation performance, which happens to be in the state of the art, is demonstrated with Spanish-to-English and English-to-Spanish translations of the European Parliament Plenary Sessions (EPPS).
Citation
Mariño, J.B., Banchs, R., Crego, J., de Gispert, A., Lambert, P., Fonollosa, José A. R., Ruiz, M. N-gram-based machine translation. "Computational linguistics", 1 Desembre 2006, vol. 32, núm. 4, p. 527-549.
Keywords
Machine translation, N-gram
Group of research
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center
TALP - Centre for Language and Speech Technologies and Applications
VEU - Speech Processing Group

Participants

Attachments