Abstract | ||
---|---|---|
We present the NTT translation system that is experimented for the evaluation campaign of "International Workshop on Spoken Language Translation (IWSLT)." The system con- sists of two primary components: a hierarchical phrase-based statistical machine translation system and a reranking sys - tem. The former is conceptualized as a synchronous-CFG in which phrases are hierarchically combined using non- terminals. The latter uses a modified voted perceptron ap- proach with large number of features. Experiments showed that our hierarchical phrase-based model outperformed a conventional phrase-based model. In addition, our reranking algorithm further boosted the performance. |
Year | Venue | Field |
---|---|---|
2006 | IWSLT | Rule-based machine translation,Example-based machine translation,Computer science,Machine translation system,Machine translation,Phrase,Speech recognition,Synchronous context-free grammar,Machine translation software usability,Natural language processing,Artificial intelligence,Perceptron |
DocType | Citations | PageRank |
Conference | 6 | 0.58 |
References | Authors | |
13 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Taro Watanabe | 1 | 572 | 36.86 |
Junichi Suzuki | 2 | 1265 | 112.15 |
Hajime Tsukada | 3 | 449 | 29.46 |
Hideki Isozak | 4 | 6 | 0.58 |