Abstract | ||
---|---|---|
In this paper, we present a novel distortion model for phrase-based statistical machine translation. Unlike the pre- vious phrase distortion models whose role is to simply penal- ize nonmonotonic alignments(1, 2), the new model assigns the probability of relative position between two source lan- guage phrases aligned to the two adjacent target language phrases. The phrase translation probabilities and phrase dis- tortion probabilities are calculated from the N-best phrase alignment of the training bilingual sentences. To obtain N- best phrase alignment, we devised a novel phrase alignment algorithm based on word translation probabilities and N-best search. Experiments show that the phrase distortion model and phrase translation model improve the BLEU and NIST scores over the baseline method. |
Year | Venue | Field |
---|---|---|
2005 | IWSLT | Rule-based machine translation,Computer science,Machine translation,Machine translation system,Phrase,Speech recognition,NIST,Natural language processing,Transfer-based machine translation,Artificial intelligence,Distortion |
DocType | Citations | PageRank |
Conference | 2 | 0.46 |
References | Authors | |
5 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
kazuteru ohashi | 1 | 17 | 1.09 |
Kazuhide Yamamoto | 2 | 207 | 39.66 |
Kuniko Saito | 3 | 75 | 7.12 |
Masaaki Nagata | 4 | 573 | 77.86 |
ntt cyber | 5 | 6 | 1.62 |