Systems and methods for contextualized and quantized soft prompts for natural language understanding
US12147765B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Aug 16, 2022 |
| Grant date | Nov 19, 2024 |
| Priority date | — |
| Expiry date | Apr 27, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N20/00
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Embodiments described herein provide a soft prompt tuning technique referred to as the Vector quantized Input-contextualized Prompt (VIP). The VIP techniques has two integral properties i) instead of learning a fixed set of prompt tokens irrespective of the input, it generates a contextualized version of the soft prompts, conditional on the input text ii) it further passes the input-contextualized prompt tokens through a quantization network, inspired by Vector Quantized Transformers. The quantization network uses nearest neighbor search over a learnable codebook to train a discrete latent variable model over the prompt-space, thus generating quantized version of contextual prompt tokens. These quantized contextual prompt tokens are finally fed into the frozen language model along with the original input text.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.