Abstract | ||
---|---|---|
This article proposes a novel reordering method for efficient two-step Japanese-to-English statistical machine translation (SMT) that isolates reordering from SMT and solves it after lexical translation. This reordering problem, called post-ordering, is solved as an SMT problem from Head-Final English (HFE) to English. HFE is syntax-based reordered English that is very successfully used for reordering with English-to-Japanese SMT. The proposed method incorporates its advantage into the reverse direction, Japanese-to-English, and solves the post-ordering problem by accurate syntax-based SMT with target language syntax. Two-step SMT with the proposed post-ordering empirically reduces the decoding time of the accurate but slow syntax-based SMT by its good approximation using intermediate HFE. The proposed method improves the decoding speed of syntax-based SMT decoding by about six times with comparable translation accuracy in Japanese-to-English patent translation experiments. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1145/2499955.2499960 | ACM Trans. Asian Lang. Inf. Process. |
Keywords | Field | DocType |
comparable translation accuracy,smt problem,efficient japanese-to-english translation,slow syntax-based smt,lexical translation,japanese-to-english patent translation experiment,english-to-japanese smt,syntax-based post-ordering,syntax-based smt decoding,two-step smt,accurate syntax-based smt | Programming language,Computer science,Machine translation,Natural language processing,Artificial intelligence,Decoding methods,Syntax | Journal |
Volume | Issue | Citations |
12 | 3 | 4 |
PageRank | References | Authors |
0.37 | 38 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Katsuhito Sudoh | 1 | 326 | 34.44 |
Xianchao Wu | 2 | 64 | 6.62 |
Kevin Duh | 3 | 819 | 72.94 |
Hajime Tsukada | 4 | 449 | 29.46 |
Masaaki Nagata | 5 | 573 | 77.86 |