Abstract | ||
---|---|---|
Abstract This paper describes NTT SMT System 2008 pre- sented at the patent translation task (PAT-MT) in NTCIR-7. For PAT-MT, we submitted our strong base- line system faithfully following a hierarchical phrase- based statistical machine translation [2]. The hierar- chical phrase-based SMT is based on a synchronous- CFGs in which a paired source/target rules are syn- chronously applied starting from the initial symbol. The decoding is realized by a CYK-style bottom-up parsing on the source side with each derivation rep- resenting a translation candidate. We demonstrate the strong baseline for the PAT-MT English/Japanese translations. Keywords: Statistical Machine Translation, Hierar- chical Phrase-based SMT. |
Year | Venue | DocType |
---|---|---|
2008 | NTCIR | Conference |
Citations | PageRank | References |
2 | 0.40 | 12 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Taro Watanabe | 1 | 572 | 36.86 |
Hajime Tsukada | 2 | 449 | 29.46 |
Hideki Isozaki | 3 | 934 | 64.50 |