Parameter utilization for language pre-training
US12072955B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 22, 2021 |
| Grant date | Aug 27, 2024 |
| Priority date | — |
| Expiry date | Feb 15, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F40/20
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Embodiments are directed to pre-training a transformer model using more parameters for sophisticated patterns (PSP++). The transformer model is divided into a held-out model and a main model. A forward pass and a backward pass are performed on the held-out model, where the forward pass determines self-attention hidden states of the held-out model and the backward pass determines loss of the held-out model. A forward pass on the main model is performed to determine a self-attention hidden states of the main model. The self-attention hidden states of the main model are concatenated with the self-attention hidden states of the held-out model. A backward pass is performed on the main model to determine a loss of the main model. The parameters of the held-out model are updated to reflect the loss of the held-out model and parameters of the main model are updated to reflect the loss of the main model.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.