Knowledge-guided structural attention processing
US10366163B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Sep 7, 2016 |
| Grant date | Jul 30, 2019 |
| Priority date | — |
| Expiry date | Jan 3, 2037 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/1822
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Systems and methods for determining knowledge-guided information for a recurrent neural networks (RNN) to guide the RNN in semantic tagging of an input phrase are presented. A knowledge encoding module of a Knowledge-Guided Structural Attention Process (K-SAP) receives an input phrase and, in conjunction with additional sub-components or cooperative components generates a knowledge-guided vector that is provided with the input phrase to the RNN for linguistic semantic tagging. Generating the knowledge-guided vector comprises at least parsing the input phrase and generating a corresponding hierarchical linguistic structure comprising one or more discrete sub-structures. The sub-structures may be encoded into vectors along with attention weighting identifying those sub-structures that have greater importance in determining the semantic meaning of the input phrase.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.