Discovering Phrases in Machine Translation by Simulated Annealing - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2008

Discovering Phrases in Machine Translation by Simulated Annealing


In this paper, we propose a new phrase-based translation model based on inter-lingual triggers. The originality of our method is double. First we identify common source. Then we use inter-lingual triggers in order to retrieve their translat ions. Furthermore, we consider the way of extracting phrase trans- lations as an optimization issue. For that we use simulated annealing algorithm to find out the best phrase translations among all those determined by inter-lingual triggers. The best phrases are those which improve the translation quality in terms of Bleu score. Tests are achieved on the proceedings of the European Parliament corpora. The training is made on a corpus containing 596K parallel sentences (French-English) and tests on a corpus of 1444 sentences. With only 8.1% of the identified source phrases occurring in the test corpus, our system overcomes the baseline model by almost 3 points.
Fichier principal
Vignette du fichier
CarolineLavecchia.pdf (69.12 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00331327 , version 1 (16-10-2008)


  • HAL Id : inria-00331327 , version 1


Caroline Lavecchia, David Langlois, Kamel Smaïli. Discovering Phrases in Machine Translation by Simulated Annealing. INTERSPEECH 2008 - 9th Annual Conference of the International Speech Communication Association, Sep 2008, Brisbane, Australia. pp.2354-2357. ⟨inria-00331327⟩
137 View
227 Download


Gmail Facebook X LinkedIn More