Machine translation in continuous space
US8229729B2 · kind B2 · utility
32Cited by
7References
19Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Mar 25, 2008 |
| Grant date | Jul 24, 2012 |
| Priority date | — |
| Expiry date | Aug 20, 2030 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F40/44
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A system and method for training a statistical machine translation model and decoding or translating using the same is disclosed. A source word versus target word co-occurrence matrix is created to define word pairs. Dimensionality of the matrix may be reduced. Word pairs are mapped as vectors into continuous space where the word pairs are vectors of continuous real numbers and not discrete entities in the continuous space. A machine translation parametric model is trained using an acoustic model training method based on word pair vectors in the continuous space.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.