Name
Title | ||
|---|---|---|
Efficient Decoding for Statistical Machine Translation with a Fully Expanded WFST Model |
Abstract | ||
|---|---|---|
This paper proposes a novel method to compile sta- tistical models for machine translation to achieve efficient decoding. In our method, each statistical submodel is represented by a weighted finite-s tate transducer (WFST), and all of the submodels are ex- panded into a composition model beforehand. Fur- thermore, the ambiguity of the composition model is reduced by the statistics of hypotheses while de- coding. The experimental results show that the pro- posed model representation drastically improves the efficienc y of decoding compared to the dynamic composition of the submodels, which corresponds to conventional approaches. |
Year | Venue | Keywords |
|---|---|---|
2004 | EMNLP | machine translation |
Field | DocType | Volume |
Example-based machine translation,Computer science,Machine translation,Synchronous context-free grammar,Compiler,Statistical model,Transfer-based machine translation,Natural language processing,Artificial intelligence,Decoding methods,Ambiguity | Conference | W04-32 |
Citations | PageRank | References |
7 | 0.53 | 16 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hajime Tsukada | 1 | 449 | 29.46 |
| Masaaki Nagata | 2 | 573 | 77.86 |