Adaptive web mining of bilingual lexicon
US8306806B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 2, 2008 |
| Grant date | Nov 6, 2012 |
| Priority date | — |
| Expiry date | Aug 5, 2031 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F40/242
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Embodiments for the adaptive mining of bilingual lexicon are disclosed. In accordance with one embodiment, the adaptive mining of bilingual lexicon includes retrieving one or more bilingual web pages, wherein each of the bilingual web page including a search term and one or more additional terms. The adaptive mining also includes forming a plurality of candidate translation pairs for each of the terms and extracting one or more translation layout patterns from the plurality of candidate translation pairs. The adaptive mining further includes deriving a term translation in a second language for the search term. The term translation being derived based on a hidden conditional random field (HCRF) model that includes the one or more candidate translations, the one or more translation layout patterns, and one or more additional features. The term translation is further stored in a lexicon repository.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.