发明名称 |
Phrase to phrase joint probability model for statistical machine translation |
摘要 |
A machine translation (MT) system may utilize a phrase-based joint probability model. The model may be used to generate source and target language sentences simultaneously. In an embodiment, the model may learn phrase-to-phrase alignments from word-to-word alignments generated by a word-to-word statistical MT system. The system may utilize the joint probability model for both source-to-target and target-to-source translation applications.
|
申请公布号 |
US2004030551(A1) |
申请公布日期 |
2004.02.12 |
申请号 |
US20030402350 |
申请日期 |
2003.03.27 |
申请人 |
MARCU DANIEL;WONG WILLIAM;KNIGHT KEVIN;KOEHN PHILIPP |
发明人 |
MARCU DANIEL;WONG WILLIAM;KNIGHT KEVIN;KOEHN PHILIPP |
分类号 |
G06F17/28;(IPC1-7):G10L15/12 |
主分类号 |
G06F17/28 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|