Debiasing pre-trained sentence encoders with probabilistic dropouts
US12106050B2 · kind B2 · utility
0Cited by
1References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jan 31, 2022 |
| Grant date | Oct 1, 2024 |
| Priority date | — |
| Expiry date | Apr 2, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N20/00
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Debiasing pre-trained sentence encoders with probabilistic dropouts may be performed by various systems, services, or applications. A sentence may be received, where the words of the sentence may be provided as tokens to an encoder of a machine learning model. A token-wise correlation using semantic orientation may be determined to determine a bias score for the tokens in the input sentence. A probability of dropout that for tokens in the input sentence may be determined from the bias scores. The machine learning model may be trained or tuned based on the probabilities of dropout for the tokens in the input sentence.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.