Transforming natural language to structured query language based on multi- task learning and joint training
US12430329B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 13, 2022 |
| Grant date | Sep 30, 2025 |
| Priority date | — |
| Expiry date | Oct 31, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/084
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Techniques are disclosed for training a model, using multi-task learning, to transform natural language to a logical form. In one particular aspect, a method includes accessing a first set of utterances that have non-follow-up utterances and a second set of utterances that have initial utterances and associated one or more follow-up utterances and training a model for translating an utterance to a logical form. The training is a joint training process that includes calculating a first loss for a first semantic parsing task based on one or more non-follow-up utterances from the first set of utterances, calculating a second loss for a second semantic parsing task based on one or more initial utterances and associated one or more follow-up utterances from the second set of utterances, combining the first and second losses to obtain a final loss, and updating model parameters of the model based on the final loss.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.