N-gram-based Machine Translation
Rights accessOpen Access
This article describes in detail an n-gram approach to statistical machine translation. This approach 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).
CitationMariño, J.B.; Banchs, R.E.; Crego, J.M.; De Gispert, A.; Lambert, P.; R. Fonollosa, J.A.; Costa-jussà, M.R. N-gram-based Machine Translation. Computational Linguistics, 2006, vol. 32, núm. 4, p. 528-549.
Showing items related by title, author, creator and subject.
Martínez Garcia, Eva; España Bonet, Cristina; Màrquez Villodre, Lluís (2014-09-22)
Open AccessMost of the current Machine Translation systems are designed to translate a document sentence by sentence ignoring discourse information and producing incoherencies in the final translations. In this paper we present some ...
N-gram-based statistical machine translation versus syntax augmented machine translation: comparison and system combination Khalilov, Maxim; Rodríguez Fonollosa, José Adrián (2009-03-30)
Open AccessIn this paper we compare and contrast two approaches to Machine Translation (MT): the CMU-UKA Syntax Augmented Machine Translation system (SAMT) and UPC-TALP N-gram-based Statistical Machine Translation (SMT). SAMT ...
Barrón Cedeño, Luis Alberto; Màrquez Villodre, Lluís; Henríquez Quintana, Carlos Alberto; Formiga Fanals, Lluís; Romero Merino, Enrique; May, Jonathan (2013)
Open AccessPost-editing feedback provided by users of on-line translation services offers an excellent opportunity for automatic improvement of statistical machine translation (SMT) systems. However, feedback provided by casual users ...