Purest ever example-based machine translation : detailed presentation and assessment - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Machine Translation Année : 2007

Purest ever example-based machine translation : detailed presentation and assessment

Résumé

We have designed, implemented and assessed an EBMT system that can be dubbed the 'purest ever built': it strictly does not make any use of variables, templates or patterns, does not have any explicit transfer component, and does not require any preprocessing or training of the aligned examples. It only uses a specific operation, proportional analogy, that implicitly neutralises divergences between languages and captures lexical and syntactical variations along the paradigmatic and syntagmatic axes without explicitly decomposing sentences into fragments. Exactly the same genuine implementation of such a core engine was evaluated on different tasks and language pairs. To begin with, we compared our system on two tasks of a previous MT evaluation campaign to rank it among other current state-of-the-art systems. Then, we illustrated the 'universality' of our system by participating in a recent MT evaluation campaign, with exactly the same core engine, for a wide variety of language pairs. Finally, we studied the in uence of extra data like dictionaries and paraphrases on the system performance.
Fichier principal
Vignette du fichier
purest_ever_lepage.pdf (793.86 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-00260994 , version 1 (06-03-2008)

Identifiants

  • HAL Id : hal-00260994 , version 1

Citer

Yves Lepage, Etienne Denoual. Purest ever example-based machine translation : detailed presentation and assessment. Machine Translation, 2007, pp.251-282. ⟨hal-00260994⟩
115 Consultations
673 Téléchargements

Partager

Gmail Facebook X LinkedIn More