Neural latent variable model for spoken language understanding
US9911413B1 · kind B1 · utility
32Cited by
4References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Dec 28, 2016 |
| Grant date | Mar 6, 2018 |
| Priority date | — |
| Expiry date | Dec 28, 2036 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2015/223
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A linguist classifier, for instance intent or slot classifier, is updated using data with only partial annotation indicating overall correctness rather that specific correct intent or slot values, which are treated as “latent” (i.e., unknown) variables. Full annotation of the data is not required. A small amount of fully annotated data may be combined with a substantially larger amount of partially annotated data to update the linguistic classifier. In a specific implementation, the linguistic classifier is a neural network and the weights are trained using a reinforcement learning approach.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.