\(N\)-gram-based machine translation. (English) Zbl 1234.68422
Summary: 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).
MSC:
| 68T50 | Natural language processing |
References:
| [1] | Berger Adam, Computational Linguistics 22 (1) pp 39– (1996) |
| [2] | Brown Peter, Computational Linguistics 16 (2) pp 79– (1990) |
| [3] | Brown Peter, Computational Linguistics 19 (2) pp 263– (1993) |
| [4] | DOI: 10.1162/089120104323093294 · Zbl 1234.68400 · doi:10.1162/089120104323093294 |
| [5] | DOI: 10.1162/089120103321337421 · Zbl 1234.68428 · doi:10.1162/089120103321337421 |
| [6] | DOI: 10.1006/csla.1996.0014 · doi:10.1006/csla.1996.0014 |
| [7] | DOI: 10.1002/j.1538-7305.1949.tb00928.x · Zbl 1200.94005 · doi:10.1002/j.1538-7305.1949.tb00928.x |
| [8] | DOI: 10.1002/j.1538-7305.1951.tb01366.x · Zbl 1165.94313 · doi:10.1002/j.1538-7305.1951.tb01366.x |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
