ISCA Archive Interspeech 2008
ISCA Archive Interspeech 2008

Discovering phrases in machine translation by simulated annealing

Caroline Lavecchia, David Langlois, Kamel Smaïli

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 translations. Furthermore, we consider the way of extracting phrase translations 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.


doi: 10.21437/Interspeech.2008-600

Cite as: Lavecchia, C., Langlois, D., Smaïli, K. (2008) Discovering phrases in machine translation by simulated annealing. Proc. Interspeech 2008, 2354-2357, doi: 10.21437/Interspeech.2008-600

@inproceedings{lavecchia08_interspeech,
  author={Caroline Lavecchia and David Langlois and Kamel Smaïli},
  title={{Discovering phrases in machine translation by simulated annealing}},
  year=2008,
  booktitle={Proc. Interspeech 2008},
  pages={2354--2357},
  doi={10.21437/Interspeech.2008-600}
}