Look ahead strategy for trie-based beam search in generative retrieval
US12353454B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Oct 14, 2020 |
| Grant date | Jul 8, 2025 |
| Priority date | — |
| Expiry date | Oct 14, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F40/284
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Systems and methods are provided for generating a keyword sequence from an input query. A first text sequence corresponding to an input query may be received and encoded into a source sequence representation using an encoder of a machine learning model. A keyword sentence may then be generated from the source sequence representation using a decoder of the machine learning model. The decoder may generate a modified generation score for a plurality of prediction tokens, wherein the modified generation score is based on the respective prediction token generation score and a maximum generation score for a suffix of each prediction token. The decoder may then select the prediction token of the plurality of prediction tokens based on the modified generation score, and add the selected prediction token to the previously decoded partial hypothesis provided by the decoder.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.