Markov-based sequence tagging using neural networks
US9600764B1 · kind B1 · utility
12Cited by
1References
23Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jun 17, 2014 |
| Grant date | Mar 21, 2017 |
| Priority date | — |
| Expiry date | Sep 22, 2035 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/09
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Features are disclosed for using a neural network to tag sequential input without using an internal representation of the neural network generated when scoring previous positions in the sequence. A predicted or determined label (e.g., the highest scoring or otherwise most probable label) for input at a given position in the sequence can be used when scoring input corresponding to the next position the sequence. Additional features are disclosed for training a neural network for use in tagging sequential input without using an internal representation of the neural network generated when scoring previous positions the sequence.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.