Including statistical NLU models within a statistical parser
US6963831B1 · kind B1 · utility
33Cited by
6References
35Claims
0Family size
Assignee
Inventor
Key dates
| Filing date | Oct 25, 2000 |
| Grant date | Nov 8, 2005 |
| Priority date | — |
| Expiry date | Oct 4, 2023 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F40/216
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method and system for statistical parsing. The method involves a series of steps. The system can apply a statistical natural language understanding (NLU) model to test input for identifying substrings within the text input. The statistical NLU model can be selected for identifying a particular class of substring. The system can examine each identified substring using an inventory of queries corresponding to the reusable statistical NLU model.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.