Title | ||
---|---|---|
Modelo estocástico de traducción basado en N-gramas de tuplas bilingües y combinación log-lineal de características |
Abstract | ||
---|---|---|
This communication introduces a stochastic machine translation system based on N- gram modelling of the joint probability of bilingual texts. The basic unit of this model is called a tuple and consists of a pair of both source (to be translated) language and target language (translation) word-strings. Translation is driven by a log-linear combination of the N-gram model probability and other features, according to the maximum entropy language modelling approach. The translation performance is evaluated by means of a speech-to-speech translation tasks: translation from Spanish to English (and viceversa) of European Parliament speeches. |
Year | Venue | Keywords |
---|---|---|
2005 | Procesamiento del Lenguaje Natural | maximum entropy language modelling.,n-gram model,speech-to-speech translation,the system reaches a state-of-art performance. keywords: stochastic machine translation |
DocType | Volume | Citations |
Journal | 35 | 0 |
PageRank | References | Authors |
0.34 | 8 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
José B. Mariño | 1 | 510 | 64.66 |
Rafael Banchs | 2 | 120 | 8.91 |
Josep M | 3 | 0 | 0.34 |
Patrik Lambert | 4 | 277 | 23.36 |
José A. R. Fonollosa | 5 | 410 | 51.32 |
Marta R. Costa-Jussà | 6 | 310 | 38.67 |